# Design MCP Server

> Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

- Skill: `jiayaoqijia/design-mcp-server` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx get-skill add jiayaoqijia/design-mcp-server`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jiayaoqijia/design-mcp-server/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: jiayaoqijia (https://skillmd.com/u/jiayaoqijia)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/jiayaoqijia/design-mcp-server

---


## When to Use

- User says "I want to build a ___ MCP server"
- User has an API, database, or system they want to expose to LLMs
- User wants to plan tools before scaffolding
- Existing server needs a new capability area — two or more tools sharing a new noun or service, or any new upstream source (design the addition, not just a single tool)

Do NOT use for a single tool on an existing noun — use `add-tool` directly.

## Inputs

Gather before designing. Ask the user if not obvious from context:

1. **Domain** — what system, API, or capability is this server wrapping? Or is the server providing internal capability with no external dependency (computation, text/code utilities, in-memory state)?
2. **Data sources / source of truth** — APIs, databases, file systems, external services? Or is the server itself the source (in-memory state, pure computation, local-only utility, embedded model)?
3. **Target users** — what will the LLM (and its human) be trying to accomplish?
4. **Scope constraints** — read-only? write access? admin operations? what's off-limits?
5. **Deployment** — local stdio, hosted HTTP, Cloudflare Workers? The answer gates primitives: DataCanvas and `MirrorService` don't run on Workers, and a tool that asks the caller for input mid-call needs a stateful HTTP session (see the Client round-trip row in Step 3).

If the domain has a public API, read its docs before designing. For internal-only servers, skip API research and go straight to user goals. Don't design from vibes either way.

### Server scope and audience

Before committing to a server boundary, answer: **what workflow does this server serve, and who is the audience?**

The unit of a server is a *user workflow*, not an API. A single rich API can earn its own server when the audience is large and the API surface supports a full workflow (PubMed for literature research, SEC EDGAR for financial analysis, Shodan for internet-wide device intelligence). Multiple APIs should collapse into one server when they serve the same workflow from different angles — a "threat intelligence" server that aggregates VirusTotal, AbuseIPDB, and GreyNoise is more useful than three separate servers because the user's goal is "assess this indicator," not "query VirusTotal."

**Don't default to one-API-one-server.** That's the right call when the API is deep enough and the audience is large enough, but it's not the starting point. The starting point is the workflow:

| Signal | Server boundary |
|:-------|:----------------|
| Single API with rich surface, large audience | Standalone server named for the platform (`pubmed-mcp-server`, `secedgar-mcp-server`) |
| Multiple APIs serving the same workflow | One server named for the workflow (`threat-intel-mcp-server`), APIs are internal sources |
| Domain with distinct sub-audiences | Consider splitting — a pentester and a SOC analyst have different workflows even in the same domain |
| Pure computation, no external deps | Standalone server named for the capability (`calculator-mcp-server`, `pentest-mcp-server`) |

When multiple APIs collapse into one server, the tool surface is organized around what the user is doing, not which API gets called. The agent says "investigate this domain" and the server routes to the best available source internally. Individual APIs become service-layer implementation details, not tool-surface identities.

## Server Naming

Usually settled before this skill runs; confirm it passes one test before designing against it. A name is earned when someone reading only the name — an npm result, a marketplace grid — forms no wrong expectation about scope. Name a wrapper for its source (`pubmed-mcp-server`, `secedgar-mcp-server`); a generic domain name is earned only by aggregating independent sources (`threat-intel-mcp-server`), and a single-jurisdiction scope goes in the name (`uk-legislation-mcp-server`). Spell out an acronym that reads as something else (`libofcongress`, not `loc`), or pair it with its domain (`eia-energy`, `bls-labor`). The tool prefix is a separate, stable identifier (see the Design table) — it need not move when the package is renamed, and renaming it is a breaking change for every client.

## Steps

### 1. Research External Dependencies

**Applies when:** the server wraps an external API or service. Skip for internal-only servers (computation, local file ops, in-memory state, code analysis utilities) and jump to Step 2.

Before designing, verify the APIs and services the server will wrap. Read the docs, then **hit the API** — real requests reveal what docs omit.

Research inline by default — fetch docs, read SDK readmes, confirm assumptions before committing them to the design. For each external dependency:

- Fetch API docs, confirm endpoint availability, auth methods, rate limits
- Check for official SDKs or client libraries (npm packages)
- Note any API quirks, pagination patterns, or data format considerations
- Read the terms of use: whether storing, caching, or redistributing the data is permitted, whether AI or LLM use is, and what attribution the data carries. Note the credential model too — keyless, one operator key, or a key each user supplies. The terms decide whether the server can be hosted for others at all, whether a local mirror is allowed, and what the server instructions must credit.

When research is genuinely parallelizable (multiple independent APIs, several SDKs to evaluate), spawn background agents for the independent legs while you proceed with domain mapping. Skip the overhead for a single API — just read it yourself.

**Live API probing.** After reading docs, make real requests against the API to verify assumptions:

- **Response shapes** — confirm actual field names, nesting, and types. Docs frequently lag or omit fields.
- **Batch/filter endpoints** — look for `filter.ids`, bulk GET, or query-by-multiple-IDs patterns. A single batch request replaces N individual fetches and eliminates serial-request bottlenecks and rate-limit accumulation.
- **Field selection** — check if the API supports `fields` or `select` parameters to request only the data you need. This reduces payload size dramatically for large objects.
- **Pagination behavior** — verify token format, page size limits, and what happens when results exceed one page.
- **Error shapes** — trigger real 400/404/429 responses to see the actual error format, not just what docs claim.
- **Unknown-param behavior** — send one deliberately misspelled parameter. If the API silently ignores it (plausible but unfiltered results instead of an error), every typo'd or unverified param name becomes a silent-wrongness bug — the service layer then needs a strict allowlist of confirmed spellings, and new filters require a probe before they ship.
- **Omission semantics** — for each major optional parameter, check what omitting it actually returns. Some APIs default to the intuitive scope; others silently widen (all historical versions, all statuses, global instead of regional). A default that changes result *meaning* becomes a server-side default plus an echoed output field, not something left to the agent.
- **Branch frequency, for bundled or bulk data** — when the "API" is a dataset the server ships, probe not only whether each record shape exists but what *fraction* of records takes it: count the records where an optional field is absent, where a value is an array instead of a scalar, where an id maps to many keys rather than one, where a status is missing. A shape found in 0.1% of records is an edge case to handle; one found in 70% is the main path, and a design that specifies only the scalar case leaves the implementer to invent the common one.

**Stopping condition:** at minimum, probe one list/search endpoint, one single-item GET, one error case (force a 404 or 400), and one unknown-param request. For large APIs with many resource types, add one probe per major noun. Stop when the response shapes and error envelope are confirmed.

This step prevents building a service layer against assumed response shapes that don't match reality.

Probe with real data; write the design with made-up data. Every example value that reaches `docs/design.md` — names, emails, phone numbers, hosts, IP addresses, identifiers tied to a person — is synthetic, and no key, token, or private hostname appears in it. The doc is tracked, and git history keeps whatever its first commit carried.

### 2. Map User Goals, Then Domain Operations

Start with **user goals**, not endpoints. Enumerate the outcomes an agent (and its human) will actually try to accomplish with this server — usually 3–10, scaled to domain size. These drive the workflow tools that form the spine of the surface. Endpoint-inventory-first design produces 1:1 API mirrors; goal-first design produces tools agents reach for. For internal-only servers, goals map to capabilities rather than endpoints — e.g., "format markdown to GFM," "tokenize text by model," "compute file hash."

Example user goals for a project management server:

- Find tasks I'm assigned to that are due soon
- Create a task in a project, assign it, and notify the owner
- Mark a task complete and log the outcome
- Audit a project's overdue work

Then enumerate the underlying **domain operations** the system supports, grouped by noun. These are the raw material workflow tools compose and single-action tools back-fill where workflows don't cover an edge case.

| Noun | Operations |
|:-----|:-----------|
| Project | list, get, create, archive |
| Task | list (by project), get, create, update status, assign, comment |
| User | list, get current |

The user-goal list shapes the tool surface; the operation list fills in the gaps. Not every operation becomes a tool — an operation stays as raw material (not its own tool) when it's already fully covered by an existing tool's output, or when the only agents who'd use it are in scenarios outside this server's stated purpose.

### 3. Classify into MCP Primitives

**Tools are the primary interface.** Not all MCP clients expose resources, and those that do rarely surface one to the model without a human selecting it. Design the tool surface to be self-sufficient: an agent with only tool access should be able to do everything the server is built for. Resources add convenience for clients that support them (injectable context, stable URIs), but are not a reliable access path.

| Primitive | Use when | Examples |
|:----------|:---------|:--------|
| **Tool** | The default. Any operation or data access an agent needs to accomplish the server's purpose. | Search, create, update, analyze, fetch-by-ID, list reference data |
| **App Tool** | **Rare — default to a standard tool.** Only when a human will actively interact with the result in real time *and* the target client supports MCP Apps. Most clients are tool-only and most agent workflows are read-by-LLM, not viewed-by-human. App tools add an iframe + CSP, `app.ontoolresult`/`callServerTool` plumbing, host-context wiring, and a `format()` text twin that still has to be content-complete (since most clients only see that). Two surfaces to keep in sync, two failure modes per change. | Dense tabular state a human scrubs through; form-based human approval in an MCP Apps-capable client |
| **Resource** | *Additionally* expose as a resource when the data is addressable by stable URI, read-only, and useful as injectable context. | Config, schemas, status, entity-by-ID lookups |
| **Prompt** | Reusable message template that structures how the LLM approaches a task | Analysis framework, report template, review checklist |
| **Client round-trip** | Not a registered primitive — a handler *returns* `ctx.requestInput(...)` to ask the client for what only it has, and is re-entered with the answer: a confirmation or form (`inputRequired.elicit`), an authorization or hosted-form URL (`inputRequired.elicitUrl`), the client model's judgment (`inputRequired.createMessage` — borrow the caller's model rather than bundling one), filesystem roots (`inputRequired.listRoots`). Design it into the tool that needs it; see Workflow tool safety and `api-context`. A server with any such tool declares `createApp({ sessionMode: { default: 'stateful', require: 'stateful' } })` — under stateless HTTP a 2025-era client's round trip is refused, so the tool is unusable rather than guarded. | Destructive-arm confirmation, OAuth consent, summarize-with-the-client's-model |
| **Neither** | Internal detail, admin-only, not useful to an LLM | Token refresh, webhook setup, migrations |

What the tool surface needs to cover depends on the server: a read-only research server has different economics than a CRUD project management server. Consider the domain, the expected agent workflows, whether it wraps one API or many, and what data relationships exist.

**Common traps:**

- **Data locked behind resources**: If something an agent needs is only accessible via a resource, it's invisible to tool-only clients. That data might warrant its own tool, or it might already be covered by an existing tool's output — but it needs a tool path somewhere.
- **CRUD explosion**: Don't map every REST endpoint to a tool. Related operations on the same noun often belong in one tool with an `operation`/`mode` parameter (see Step 4).
- **1:1 endpoint mirroring**: API endpoints are designed for programmatic consumers. LLM tools should be designed for workflows — what an agent is *trying to accomplish*, not what HTTP calls happen under the hood.

**Irreversible operations stay in the UI.** The "Neither" bucket above covers operations that aren't useful to an LLM. There's a second, sharper reason to exclude something from the tool surface: operations whose failure mode is catastrophic and unrecoverable. Examples span domains — dropping a production database table (data loss across every row), force-emptying a versioned cloud-storage bucket (no recovery once the lifecycle policy fires), revoking the workspace's last admin role (locks everyone out, recovery requires vendor support), GDPR permanent-delete on a customer profile (un-restorable by design), purging an analytics warehouse partition older than the retention window (auditable history gone), or deleting the single audience on a free-plan email platform (nukes every subscriber and historical report in one call). These are useful to an LLM *in principle*, but the blast radius of a mis-call is disproportionate to any agent workflow. Humans do these in the vendor UI, where confirmation dialogs and undo paths exist. Agents shouldn't have the tool at all.

This is distinct from `destructiveHint` — that annotation is for operations that are destructive but recoverable (deleting a task, reverting a commit) and agents should still have them. The "stays in the UI" line applies only to operations whose failure is both catastrophic *and* irreversible.

### 4. Design Tools

This is the highest-leverage step. Tool definitions — names, descriptions, parameters, output schemas — are the **entire interface contract** the LLM reads to decide whether and how to call a tool. Every field is context. Design accordingly.

#### Tool shapes you'll encounter

Most tools follow the `{server}_{verb}_{noun}` default — one focused responsibility, one clear verb, often (but not always) one upstream call. API-wrapping examples: `pubmed_search_articles`, `pubmed_fetch_articles`. Internal-only examples: `markdown_format_text`, `regex_test_pattern`, `tokens_count_text` — same naming convention, no external dep. Three variants warrant explicit design pressures of their own:

| Shape | Purpose | Typical form | Examples |
|:------|:--------|:-------------|:---------|
| **Workflow** | Multi-step orchestration that replaces a common agent chain | N upstream calls (often parallelized); may request confirmation; may need mid-flow cleanup | `clinicaltrials_find_eligible` (search → filter → rank) |
| **Instruction** | State-aware procedural guidance — advice, not action | Static markdown + a few live-state fetches, `readOnlyHint: true`, outputs `nextToolSuggestions` pre-filling the recommended follow-up. No writes. | `git_wrapup_instructions` |
| **Reference** | Decode opaque domain vocabulary — codes, enums, identifier formats, coverage windows — so agents can build valid inputs for the rest of the surface | Static tables or one cached fetch (often zero upstream calls); consolidate N lists under one `topic` enum; `readOnlyHint: true`, `openWorldHint: false` when offline | `medcode_list_systems`, `osv_list_ecosystems` |

These aren't boxes every tool must fit into — some blend shapes — but the design pressures differ enough that naming them helps avoid re-discovering the patterns per server.

#### Think in workflows, not endpoints

The unit of a tool is a *useful action*, not an API call. Ask: "What is the agent trying to accomplish?" — not "What endpoints does the API have?"

A single tool can call multiple APIs internally, apply local filtering, reshape data, and return enriched results. The LLM doesn't know or care about the underlying calls.

```ts
// Workflow tool — search + local filter pipeline, not a raw API proxy
const findEligible = tool('clinicaltrials_find_eligible', {
  description: 'Match a patient profile to eligible clinical trials, filtering by age, sex, conditions, location, and healthy volunteer status. Results are ranked and carry a per-study eligibility explanation.',
  // handler: listStudies() → filter by eligibility → rank by location proximity → slice
});
```

> **Tip — mode consolidation.** When a tool has several related operations on the same noun, you can consolidate them under one tool with a `mode`/`operation` enum. This affects both naming (noun-led, e.g., `github_pull_request`) and handler design (dispatch by mode). Use when it tightens the surface; skip when ops diverge enough to warrant separate tools. When the arms need *different* required fields (look up by ID vs. search by name), declare the input as `z.discriminatedUnion('mode', [...])` rather than making every field optional and checking the combination by hand — each arm advertises its own `required`, the handler narrows on the discriminator, and mixed arguments are rejected. Two constraints: `output` stays a flat `z.object`, and a union root rules out `headerParam`. See `add-tool` § *Multi-mode tools*.

#### Multi-source tools and fallback chains

**Applies when:** a server aggregates multiple data sources for the same workflow, and the "best" source varies by input type, availability, or coverage. Skip for single-API servers.

When a tool's goal can be served by multiple sources, design it as a **multi-source tool** — the agent calls one tool, the handler routes to the best source (or fans out to several) internally. This is the difference between a "PubMed wrapper" and a "literature research server": a hypothetical `literature_search_articles` tries PubMed first, falls back to EuropePMC for broader coverage, then Unpaywall for open access. The agent doesn't choose which API to hit — the server makes that decision based on what works.

Two patterns:

**Source fallback chains** — try sources in priority order, fall through on failure or empty results. Best when sources cover the *same corpus* with different depth or availability. The output should indicate which source provided the data so the agent (and human) can assess provenance. When the fallback changes what is being searched — a different corpus, different identifiers, different licensing — don't chain: expose the second source as a sibling tool so the agent chooses the corpus knowingly (the shipped `pubmed-mcp-server` keeps `pubmed_europepmc_search` separate for exactly this reason).

**Multi-source fan-out** — query multiple sources in parallel, merge results. Best when sources provide complementary data about the same entity. Use `Promise.allSettled` so one *unavailable* source doesn't tank the whole call — but a rejected input is wrong for every source. Rethrow an input-class rejection (`ValidationError`, `InvalidParams`) from any source instead of folding it into a per-source failure: a source that ignores the bad value would otherwise answer for it, and the agent reads a caller mistake as an outage to retry.

```ts
// Handler pseudocode — indicator enrichment across threat intel sources
async handler(input, ctx) {
  const settled = await Promise.allSettled([
    vtService.lookup(input.indicator),
    abuseIpService.check(input.indicator),
    greynoiseService.query(input.indicator),
  ]);
  for (const r of settled) {
    if (r.status === 'rejected' && isInputError(r.reason)) throw r.reason; // the caller's mistake, not an outage
  }
  const [vt, abuse, greynoise] = settled;
  return {
    indicator: input.indicator,
    sources: {
      // { status: 'ok', data } | { status: 'unavailable', error } — provenance per source
      virustotal: toSourceResult(vt),
      abuseipdb: toSourceResult(abuse),
      greynoise: toSourceResult(greynoise),
    },
    // Server synthesizes a verdict from the sources that answered — the agent gets a conclusion, not raw API dumps
    assessment: synthesizeVerdict(vt, abuse, greynoise),
  };
}
```

In both patterns, the tool surface is organized around what the user is doing. Sources are service-layer details — the agent sees `threat_enrich_indicator`, not `virustotal_lookup` + `abuseipdb_check` + `greynoise_query`. Mode-based dispatch by input type (e.g., `indicator_type: 'ip' | 'domain' | 'hash'`) naturally routes to different source chains per mode, since different sources cover different indicator types.

#### Cut the surface

There is no fixed ceiling on tool count and no target either. The ceiling is workflow coverage — if the domain genuinely has 20 distinct workflows, expose 20 tools; the cut is per-tool overlap and reach. After mapping tools, review the full list critically. A tool that covers a niche use case, serves a tiny fraction of agents, or duplicates what another tool already handles is a candidate for deferral. Drop it from the design and note it as a future addition if demand warrants. Every tool in the surface is cognitive load for tool selection — a tight surface outperforms a comprehensive one.

#### Instruction tools

**Applies when:** the domain has recurring "how do I do X well given my current state" questions worth merging with static procedural content. Skip otherwise.

Some domains benefit from a tool whose output is **guidance, not data** — a markdown playbook tailored by live account state, with pre-filled next-step tool calls. These sit between Prompts (static templates, client-invokable) and action tools (do work, return data): they return advice, but the advice is worth more than static text because it merges procedural content with the agent's actual situation.

Characteristics:

- **Output is markdown guidance**, not structured data (though the output schema still has fields — typically `guidance`, `diagnostics`, and `nextToolSuggestions`)
- **Merges static procedural content with live state** — the value is the tailoring. "You have 12 staged files spanning 4 unrelated changes — split them into separate commits before pushing" beats a generic best-practices article. The same shape works in other domains: "Your slowest query is 2.3s on `orders.customer_id` — add the index before tuning the planner" (database advisor), "Error rate spiked 4× at 14:32 UTC, 4 minutes after the `web@a3f9c2` deploy — roll back before chasing the upstream provider" (incident triage).
- **`readOnlyHint: true`; `openWorldHint` follows where the diagnostics come from** — `false` when the live state is local (a repo on disk), `true` when it is fetched from an external API. No writes either way.
- **Outputs `nextToolSuggestions`** — an array of recommended follow-up tool calls with arguments **pre-filled** from the diagnostics, not just tool names. The agent consumes the playbook, then executes steps with other tools.
- **Consolidate by `topic` enum** — what could be N separate per-topic tools collapses into one

```ts
const wrapupInstructions = tool('git_wrapup_instructions', {
  description: 'Get procedural guidance tailored to the current repo state: best-practice markdown merged with live diagnostics (staged/unstaged files, branch info, recent commits) and pre-filled follow-up tool calls. Read-only; execute the steps with other tools.',
  annotations: { readOnlyHint: true, openWorldHint: false },
  input: z.object({
    topic: z.enum(['review-changes', 'stage-and-commit', 'push-to-remote'])
      .describe('Playbook topic. Determines which static guidance is returned and which live state is fetched for tailoring.'),
  }),
  output: z.object({
    guidance: z.string()
      .describe('Markdown playbook content, tailored to current account state.'),
    diagnostics: z.record(z.string(), z.unknown())
      .describe('Live state used to tailor the guidance (e.g., staged file count, branch divergence, recent commit cadence).'),
    nextToolSuggestions: z.array(z.object({
      toolName: z.string().describe('Tool to call next.'),
      reason: z.string().describe('Why this step is recommended given current state.'),
      args: z.record(z.string(), z.unknown()).describe('Arguments pre-filled from diagnostics; {} when the tool takes none.'),
    })).describe('Recommended follow-up calls with arguments already populated.'),
  }),
});
```

Prior art: [`git_wrapup_instructions`](https://github.com/cyanheads/git-mcp-server) walks through staging, commit, and push with repo state inspected. If a server has recurring "how do I do X well given my state" questions, an instruction tool typically beats N topic-specific tools and duplicating guidance in tool descriptions.

**One suggestion shape, every server.** Each entry is exactly `{ toolName, reason, args }` — no per-server renames (`tool`, `rationale`, `suggestedArgs`, `arguments`), which force every client to special-case every server. `args` is always present (`{}` for a tool that takes none), and the array is always present, empty when nothing is worth suggesting. A tool on another server is never an entry: this server cannot know it is installed, so name it in the `guidance` prose instead.

**Data tools qualify on the same terms.** A data tool carries `nextToolSuggestions` when the right next call depends on its own result and the arguments come from that result — a status sweep that finds a degraded vendor, a connect call that learns which services the upstream supports. A fixed chain (search → get by the returned ID) does not: the IDs in the result and the server instructions already carry it, and a suggestion on every call is token noise.

**Suggestions are scoped to what this deployment registers.** A `nextToolSuggestions` entry is an executable call, so it is only correct when its target is enabled under the same configuration — a tool wrapped in `disabledTool()` is absent from `tools/list`, and a suggestion naming it hands the agent a call that fails on dispatch. Build the array from the same config the registration reads, and when the target is off, drop the entry rather than the explanation: `guidance` can still say the capability is unavailable in this deployment and what to do instead. The audit and a worked example live under *Feature-flagged tools* in `add-tool/SKILL.md`.

#### Reference tools

**Applies when:** the domain speaks in opaque vocabulary — enum codes, classification systems, identifier formats, per-source coverage windows — that agents must supply as inputs elsewhere. Skip when inputs are self-evident (free text, ISO dates, well-known formats).

A reference tool is the surface's decoder ring: which codes exist, what they mean, what format each identifier takes, what each source covers. Consolidate what could be N per-list tools under one `topic` enum, and serve it from static tables or a cached fetch so it stays cheap to call. Its second job is structural: it is the standing **target of recovery routing** — error `recovery` strings, zero-hit notices, and resolver guidance across the surface end with "consult the reference tool, topic X" (see Error design), which only works when the tool exists. Implement it first — it usually has no service dependency, and it grounds field-testing for every other tool.

#### Workflow tool safety

**Applies when:** a tool performs multi-step mutations with destructive modes (`send`/`apply`/`promote`) that benefit from human confirmation before the irreversible step fires. Skip for read-only or idempotent workflows.

Tools that perform multi-step mutations (the Workflow shape) have two safety considerations beyond single-call tools. Both are about giving the agent — and the human behind it — a chance to catch a bad invocation before it commits.

**Confirmation-gated destructive modes, with an annotation fallback.** When a workflow's `mode` parameter switches between safe and destructive arms (`draft` vs `send`, `plan` vs `apply`), gate the destructive arm on a confirmation the handler asks for via `ctx.requestInput(...)`, so a human approves before the irreversible step fires. The handler is re-entered with the answer on `ctx.inputs`; it does not `await` mid-call. The answer alone does not prove the prompt was shown — a client can send one unasked, and any `requestState` replays within its lifetime — so the gate stores the operation, the caller, the confirmed target, and a hash of what it holds in a `ctx.state` record keyed by a random id, sends only that id as `requestState`, and redeems the record before the destructive arm runs (`api-context` § *Consent gates*). Plan shared storage for that record when a 2026-07-28 retry can reach another instance (`filesystem`, `supabase`, or `cloudflare-d1` — not `cloudflare-kv`), and set `MCP_REQUEST_STATE_KEY` so a retry can only carry state the server minted. Redeeming is not atomic — concurrent retries on one id can each pass the gate until `ctx.state` gains an atomic `take` ([#593](https://github.com/cyanheads/mcp-ts-core/issues/593)) — so an arm that must not run twice is idempotent per record.

The gate is always *reachable* — `ctx.requestInput` is present on every transport and both protocol revisions (2025-11-25 legacy, 2026-07-28 current) — but it is not always *answerable*: a client that never fulfils the `input_required` result simply doesn't retry, and — with the record pattern, which proceeds only on a record it redeemed — the destructive step never runs. The same holds for a 2025-11-25 HTTP client when the server runs `MCP_SESSION_MODE=stateless`: the legacy round-trip shim still runs, but its capability gate refuses because the serving instance never processed `initialize` — the destructive step never fires. That is the safe outcome, but it makes the tool unusable for those clients, so a server built around such a gate declares `createApp({ sessionMode: { default: 'stateful', require: 'stateful' } })` and refuses to start stateless rather than degrading (`api-context` § `ctx.requestInput`). Keep `destructiveHint: true` in annotations so those clients' own approval flows still surface the risk. A decline is terminal — the handler fails the call rather than re-asking, which would loop until the round budget runs out. `ctx.clientCapabilities` never decides whether to ask: a gate that skips its prompt when `elicitation` is undeclared is the bypass the gate exists to prevent.

**Safe defaults on parameters that determine blast radius.** When a workflow accepts a parameter that controls how far-reaching a mutation is, default to the safer value. A bulk file-update tool defaulting `mode: 'preview'` (no writes) means a sloppy agent call shows a diff rather than blasting changes; an apply-plan tool defaulting `dryRun: true` means a misread plan previews rather than executes; an object-delete tool requiring an explicit `confirmCount` matching the result-set size means an unscoped query can't silently nuke a million rows. Agents that genuinely want the destructive behavior have to name it explicitly, which surfaces intent in the tool call and in logs.

**Make retried writes safe.** Agents re-issue a call that timed out. A write that can double-apply (create, send, charge, enqueue) takes a caller-supplied idempotency key or resolves to upsert semantics — and only then earns `idempotentHint: true`.

#### Tool descriptions

The description is the LLM's primary signal for tool selection. It must answer: *what does this do, and when should I use it?*

- **Imperative present tense, capability first.** "Search for clinical trial studies using queries and filters" beats "Interact with studies", and beats "Searches for…", "This tool…", "Allows you to…". The `tool-defs-analysis` skill audits this across a finished surface.
- **Include operational guidance when it matters.** If the tool has prerequisites, constraints, or gotchas the LLM needs to know, say so in the description. Don't add boilerplate workflow hints when the tool is self-explanatory.
- **Prefer a single cohesive paragraph.** Pack operational guidance into prose sentences (separated by periods or em-dashes) rather than bullet lists or blank-line-separated sections. Descriptions render inline in most clients, and bullet structure reads as visual noise rather than signal. Operation-by-operation bullets also duplicate info that already lives in the `operation` enum's `.describe()`.
- **Don't leak.** Descriptions are for the consumer, not the author. Three categories to audit against:
    - *Implementation details* — endpoint paths, API call counts, internal parameter mappings, routing logic. Describe what the tool does and when to use it, not how it's wired up.
    - *Meta-coaching* — directives about how to use the output. "Treat X as the canonical Y", "callers should…", "the LLM should…". The description sells the tool; it doesn't coach the reader.
    - *Consumer-aware phrasing* — references to "LLM", "agent", "Claude", or any specific reader. The description shouldn't name who's reading it.

```ts
// Good — describes a prerequisite the LLM must know
description: 'Set the session working directory for all git operations. This allows subsequent git commands to omit the path parameter.'

// Good — self-explanatory, no workflow hints needed
description: 'Show the working tree status including staged, unstaged, and untracked files.'

// Good — warns about constraints
description: 'Fetch trial results data for completed studies. Only available for studies where hasResults is true.'
```

Descriptions should be as long as needed — concise but complete. Don't artificially truncate, and don't pad with filler.

#### Parameter descriptions

Every `.describe()` is prompt text the LLM reads. Parameters should convey: what the value is, what it affects, and (where non-obvious) how to use it well.

- **Constrain the type.** Enums and literals over free strings. Regex validation for formatted IDs. Ranges for numeric bounds.
- **The input root is already strict.** `tool()` applies `.strict()` at the root and advertises `additionalProperties: false`, so an unknown top-level key is rejected by name instead of silently stripped; nested objects still strip unless made strict themselves. Open the root with `.passthrough()` (Zod 4 also spells it `.loose()`; `tool()` honors either) only on a tool that deliberately proxies arbitrary upstream parameters (a raw-query tool), and say so in its description.
- **A blank optional string is unset.** Form-based clients send every optional field they display as `""`. Treat the blank as omitted — left off the upstream request, never forwarded as `param=`, which some APIs read differently from omission — and never design a `.min(1)` onto an optional field to catch it. `add-tool` has the schema pattern that keeps a validator on the field.
- **Numeric bounds earn their `.max()`.** An output-only ceiling the content already bounds (`maxSections`, a character budget) takes none: a larger value means no limit. A workload cap (an ID batch, `limit`) keeps a hard ceiling against absurd input. Between the per-call cap and that ceiling, a read — or an operation whose contract allows partial completion — processes up to the cap and names the remainder, disclosed like a capped list (below), since a rejection for a value with one obvious reading only costs the caller a round trip. A write, destructive, or otherwise atomic batch over its cap rejects before doing anything, naming the cap, so its `.max()` is the cap itself: doing the first items and naming the rest splits one intended operation in two and leaves the caller to work out which items changed.
- **Use JSON-Schema-serializable types only.** The MCP SDK serializes schemas to JSON Schema for `tools/list`. Types like `z.custom()`, `z.date()`, `z.transform()`, `z.bigint()`, `z.symbol()`, `z.void()`, `z.map()`, `z.set()` throw at runtime. Use structural equivalents (e.g., `z.string().describe('ISO 8601 date')` instead of `z.date()`).
- **Explain costs and tradeoffs** when a parameter choice has meaningful consequences.
- **Name alternative approaches** when a simpler path exists.
- **Include format patterns** for structured values, but don't pad descriptions with redundant examples.

```ts
// Good — explains cost, recommends action, names the alternative
fields: z.array(z.string()).optional()
  .describe('Specific fields to return (reduces payload size). Without this, the full study record (~70KB each) is returned. Use full data only when you need detailed eligibility criteria, locations, or results.'),

// Good — explains what the flag does AND how to override
autoExclude: z.boolean().default(true)
  .describe('Automatically exclude lock files and generated files from diff output to reduce context bloat. Set to false if you need to inspect these files.'),

// Good — names the format and gives one example
nctIds: z.union([z.string(), z.array(z.string()).max(5)])
  .describe('A single NCT ID (e.g., "NCT12345678") or an array of up to 5 NCT IDs to fetch.'),
```

**Input-edge normalization.** For every identifier, code, or enum-ish input, enumerate at design time the variants a caller will plausibly send, and decide per variant: normalize, or error. The rule is **normalize what is certain, error on what is ambiguous.** A variant is certain when the mapping is unambiguous, one-to-one, and preserves the submitted meaning exactly — then the call succeeds instead of returning a miss for a value the server could resolve. Everything short of that is an error naming the expected shape, with a `recovery` routing to the reference tool. Never fuzzy-match a value, broaden a query, swap one entity for another, or drop a filter to make a call succeed: plausible-looking rows from a guessed input are worse than a rejection the agent can act on.

| Class | Example | Handling |
|:---|:---|:---|
| Case or bare-leaf shorthand of a code | `ACS5`, `acs5` → `acs/acs5` | Normalize before lookup |
| Domain value alias | `mph` → `m/h`, `kph` → `km/h` | Alias table at the input edge |
| Composite identifier completed by context | `part: "52"` + `section: "21"` → `52.21` | Try as-given first, retry the composed form on a miss — never rewrite unconditionally, since the bare form can be legitimate |
| Delimiter-joined list where an array is accepted | `"US,JP,KR"` → `["US","JP","KR"]` | Split on the documented separator |
| Spelled-out vs. abbreviated name | `"Houston, Texas"` → `"Houston, TX"` | Normalize against the bundled name table |

These are **value**-level, and the mappings are domain knowledge — settle them per input in the design doc's param table. Argument **key** names are not: the framework rewrites declared and case-style key aliases and drops client-added root keys before the schema sees the arguments, and, against the tool's own schema after a failed parse, repairs a JSON-stringified array or object, an integer sent for a string, a number or boolean sent as a string, 

…(truncated)
