Connect agents to the Data API builder MCP endpoint
The MCP endpoint is the same Data API builder runtime as REST and GraphQL: the same entities, the
same roles and the same permissions, offered to an agent as a fixed set of tools. What breaks is
everything between the client and those tools, and on version 2.1 most of those failures arrive
inside an HTTP 200.
Verified against Data API builder 2.1.5 with raw JSON-RPC requests over Streamable HTTP, against
a container built from the 2.1.5 image and a SQL engine in a container. Client configuration
formats are from the Visual Studio Code MCP reference and Microsoft Learn; they have not been
exercised against a hosted endpoint. How the server description reaches the client was read from
the 2.1.5 source, not measured.
The boundary
| Question |
Owner |
| Running the endpoint locally and adding it to the workspace MCP configuration, in VS Code |
The MSSQL extension's Data API builder view |
Per-entity MCP settings, descriptions and anonymous/authenticated permissions, in VS Code |
The MSSQL extension's Data API builder designer |
Hosting it in Azure, runtime.mcp.allowed-hosts, replicas, health |
deploy-dab-to-azure |
| The identity DAB uses to reach the database |
entra-id-auth |
This skill owns the hosted endpoint: the client, its credential and role selection, the settings the
designer does not set, and proving what the agent can reach.
What the endpoint is
POST /mcp, Streamable HTTP, protocol version 2025-06-18. serverInfo.name is
SQL MCP Server. Clients send Accept: application/json, text/event-stream; replies arrive as
event: message frames. A browser opening /mcp sees an error; that is not a fault.
initialize returns an Mcp-Session-Id header. Every later request carries it. The session
lives in the process that issued it.
- Seven tools, the same list for every caller. Their configuration keys under
runtime.mcp.dml-tools name them: describe-entities, read-records, create-record,
update-record, delete-record, execute-entity, aggregate-records; clients show the same
names with underscores. There is no free-form SQL and no schema change. Stored procedures run
through the execute tool, or as named tools of their own.
runtime.mcp.description is returned to the client as instructions at initialize. It is the
only text that tells the agent what this server is for; see
Tell the agent what this server is for.
dab start --mcp-stdio role:<role> is for local clients only. It uses the development
Simulator provider and never reaches a hosted endpoint. Over stdio, 2.1.5 sends the
description only as serverInfo.description, a human-readable field, with no instructions,
when the client negotiates protocol 2025-11-25, so a local client may never give it to the
model.
Four things that fail while looking fine
Each observed on 2.1.5 when this skill was written, with an entity granted only to authenticated.
To the user they are documentation, not something you measured: say so, and name what you did not run.
tools/list is not a permission check. An anonymous caller was offered all seven tools,
including the delete tool, for a configuration in which it could do nothing.
- The entity-description tool said
NoEntitiesConfigured when the configuration had
entities. The caller's role could see none of them. The request reached DAB as a role with
nothing granted: usually no Authorization header arrived, so it ran as anonymous, or the
entities are granted to a named role and the client sent no X-MS-API-ROLE, so it ran as
authenticated, which inherits from anonymous and never from a named role. Do not add
anonymous permissions to make the message go away.
- A denied tool call is HTTP 200. A call to the read tool for a role without
read returned
200 with a tool result whose status is error and type is PermissionDenied. Monitoring
HTTP status alone sees success. Read the result.
Session not found (-32001) is HTTP 404 from another process. A replica that did not issue
the session, a restarted container or a new revision all answer this way. The client must call
initialize again. Scaling belongs to deploy-dab-to-azure.
A 403 whose body names the Host or Origin header is the 2.1 host allowlist, not a permission.
deploy-dab-to-azure fixes it in the configuration.
Choose inbound authentication the client can actually perform
The client's credential decides the DAB role for every tool call. The database never sees the
caller: DAB connects with its own identity for every request.
| What the client can send |
DAB provider |
Consequence |
| A Microsoft Entra bearer token for the API |
EntraID, with the token's aud and iss |
authenticated, or a named role when the client also sends X-MS-API-ROLE and the token carries that role |
| Nothing |
Unauthenticated |
Every call is anonymous; grant anonymous only narrow read |
| An API key or another scheme |
Put Azure API Management in front, which authenticates and forwards |
DAB sees what the gateway forwards |
One DAB instance has one inbound scheme. Two clients that need different schemes need two
instances. A client that cannot set custom headers cannot select a named role, so design its access
around authenticated.
Configure the client
Visual Studio Code, .vscode/mcp.json. The token is prompted for, never written to the file:
{
"inputs": [
{ "type": "promptString", "id": "dab-token", "description": "Access token for the Data API builder API", "password": true }
],
"servers": {
"sql-mcp": {
"type": "http",
"url": "https://<host>/mcp",
"headers": { "Authorization": "Bearer ${input:dab-token}", "X-MS-API-ROLE": "<role>" }
}
}
}
Drop X-MS-API-ROLE to run as authenticated. VS Code does not forward servers that need
${input:...} to Copilot harness sessions; there, use the portable .mcp.json with a top-level
mcpServers object and "Authorization": "Bearer ${DAB_TOKEN}" read from the environment.
A pasted access token expires within hours. Use it to test. For a lasting connection, use a client
that obtains tokens itself, such as a Foundry agent's Microsoft Entra authentication mode, or a
gateway.
Foundry agent. Add a tool, choose Custom, then Model Context Protocol, and enter
https://<host>/mcp as the remote endpoint. The authentication mode chosen there must match the
DAB provider; Unauthenticated in Foundry reaches only anonymous permissions.
MCP Inspector, for debugging only:
npx -y @modelcontextprotocol/inspector@2.12.0 https://<host>/mcp (pin the release you have
reviewed), then add the Authorization header in its connection settings. Do not host Inspector
where others can reach it.
Tell the agent what this server is for
Every Data API builder server offers the same seven generic tools. What this one holds, what it is
for and where it stops reach the agent through one setting, runtime.mcp.description, returned as
instructions at initialize. Entity and field descriptions say what a table or column means;
only this says what the server is for, and it is what lets an agent connected to several servers
pick this one for the right questions. Treat it as configuration, not as a comment.
| Property |
Consequence |
| One string, the same for every caller and role, returned before any permission is checked |
Anonymous callers receive it too. No secrets, internal host or server names, or entities some role must not know exist |
| It restricts nothing |
"Read-only" in the text stops no write; permissions do. Text that disagrees with the permissions misleads the agent |
| The client decides whether the model sees it |
The MCP specification makes it a hint a client may add to the model's context. Check yours |
| Read once |
DAB reads it at startup and a client receives it once per session: restart or redeploy, then reconnect |
| Blank or whitespace |
No instructions field is sent |
A useful description says, in a few sentences:
- Purpose and audience: what data this is, and which agent or task it serves.
- What is here: the entities and custom tools the agent's role can reach, and what is
deliberately not available.
- How the tools fit together: list the entities before reading, filter and select columns
instead of reading whole tables, aggregate for counts and totals.
- Limits: read-only or not, units, currencies and time zones, freshness, and the questions it
cannot answer.
Leave out what each tool's own description already says, behaviour rules unrelated to this server,
and marketing.
Weak: Product catalog
Useful: Read-only access to Contoso's product catalog and order history, for the sales assistant
answering customer questions about products, prices and past orders. Entities: Product,
Order. Prices are USD; order dates are UTC. List the entities before reading, filter and
select only the columns needed, and aggregate for counts and totals instead of reading
every row. Inventory and customer contact details are not available here.
Review it whenever you create or review a configuration with MCP enabled:
- Read
runtime.mcp.description from the file and, for a hosted endpoint, the instructions
that initialize returns.
- It is missing if absent or blank. It is insufficient if it does not cover the four points
above, or if it contradicts the permissions or the advertised tools.
- Draft a replacement that opens with what the server is for, built from the configuration: the
entities and actions the agent's role can reach, the advertised tools, custom tools, and
entities kept out of MCP. Mark what the file cannot say, such as who the agent serves and what
it must not be used for, as questions rather than guesses.
- Present the current text beside the draft. Tell the user that every caller receives it at
initialize, anonymous ones included, and that it restricts nothing. Ask them to confirm the
purpose and answer the open questions, and wait for approval or edits before writing it.
- Write it with
dab configure --runtime.mcp.description "<text>", set runtime.health.roles
again afterwards (deploy-dab-to-azure), restart or redeploy, and confirm initialize returns
the new text.
Shape what the agent sees
Permissions are the control; tool switches only change what is advertised. Do both.
In VS Code, make the per-entity settings below in the MSSQL extension's designer, which edits the
same file: descriptions, field and parameter descriptions, an entity's MCP switch, and a stored
procedure as a custom tool. The designer offers only anonymous and authenticated permissions
and no server-wide MCP settings, so named roles such as agent, the global tool switches and the
server description still go through the CLI, after the designer's edits.
# read-only agent: grant read only, then stop advertising write tools
dab update Product --permissions "agent:read"
dab configure --runtime.mcp.dml-tools.create-record false \
--runtime.mcp.dml-tools.update-record false --runtime.mcp.dml-tools.delete-record false
# keep an entity on REST but out of MCP entirely (writes "mcp": false on the entity)
dab update AuditLog --mcp.dml-tools false
# tell the agent what each entity and column means
dab update Product --description "One row per sellable product."
dab update Product --fields.name Price --fields.description "Unit price in USD."
# a curated stored procedure as its own named tool
dab add GetTopProducts --source dbo.usp_GetTopProducts --source.type stored-procedure \
--permissions "agent:execute" --mcp.custom-tool true \
--description "Returns the best-selling products." \
--parameters.name "top" --parameters.description "How many to return." --parameters.required true
With MCP enabled, 2.1.5 dab validate warns when entities carry no fields definitions. Describe
at least the key and the columns an agent filters on. Any dab configure call above resets
runtime.health.roles; deploy-dab-to-azure covers the order.
Verify with requests, not with the client UI
Run these against the hosted endpoint as the agent's own identity. Open
references/mcp-requests.md when you send them; it has the full
bodies in bash and PowerShell.
initialize returns 200, an Mcp-Session-Id header and instructions matching
runtime.mcp.description. No instructions field means no description is set.
notifications/initialized, then tools/list, carrying the session header.
tools/call on the entity-description tool lists exactly the entities this role should see.
tools/call on the read tool with {"entity": "<Entity>", "first": 1} returns one record.
- As a role that must not write, the create tool returns a tool error, not a record. Send this probe only to a
disposable copy of the database: a permission wider than intended makes it a real insert. Against production,
prove read-only from
dab configure --show-effective-permissions and skip the probe.
When it fails
| Symptom |
Cause |
Fix |
403 naming the Host or Origin header |
Host allowlist |
deploy-dab-to-azure |
| 401 |
Token missing, expired, or aud/iss mismatch |
Decode the token and compare with the configuration |
NoEntitiesConfigured with entities configured |
The caller's role sees none |
Fix the token or X-MS-API-ROLE, not the permissions |
Tool result PermissionDenied under HTTP 200 |
The role lacks that action on that entity |
dab configure --show-effective-permissions |
404 Session not found |
Session issued by another process |
Re-initialize; deploy-dab-to-azure for replicas |
| The agent picks the wrong entity or invents columns |
No descriptions or fields |
Add descriptions and fields as above |
| The agent ignores the server, uses it for questions it cannot answer, or reads whole tables |
No instructions, or text without purpose, scope or limits |
Write runtime.mcp.description as above |
Do not
- Do not commit a token to
mcp.json or .mcp.json.
- Do not treat
tools/list, an HTTP 200 or a client's green status as proof of access.
- Do not grant
anonymous to make the entity-description tool return something.
- Do not rely on disabling a tool, or on a description that says read-only, to stop writes; remove
the permission.
- Do not leave
runtime.mcp.description empty or generic, and do not put in it anything an
anonymous caller must not see. Do not rewrite it without the user's approval.
- Do not probe write denial against a production database. A probe that is not denied is a write.
- Do not state the 2.1.5 behaviours above as timeless facts, and do not call them measured, verified or
tested unless you sent the request yourself in this session. Attribute them as "documented for DAB 2.1.5
in this skill, not verified against your endpoint", and keep the user's own transcript separate from them.
1---2name: dab-mcp-endpoint3description: "Use when connecting an AI agent to a hosted Data API builder MCP endpoint, writing its server description, making its tools read-only, or diagnosing role, tool, permission or session failures, including describe_entities reporting 'no entities configured' for a configured endpoint."4metadata:5 source: https://skillmd.com/skills/microsoft/dab-mcp-endpoint6---78# Connect agents to the Data API builder MCP endpoint910The MCP endpoint is the same Data API builder runtime as REST and GraphQL: the same entities, the11same roles and the same permissions, offered to an agent as a fixed set of tools. What breaks is12everything between the client and those tools, and on version 2.1 **most of those failures arrive13inside an HTTP 200**.1415Verified against Data API builder 2.1.5 with raw JSON-RPC requests over Streamable HTTP, against16a container built from the 2.1.5 image and a SQL engine in a container. Client configuration17formats are from the Visual Studio Code MCP reference and Microsoft Learn; they have not been18exercised against a hosted endpoint. How the server description reaches the client was read from19the 2.1.5 source, not measured.2021## The boundary2223| Question | Owner |24|---|---|25| Running the endpoint locally and adding it to the workspace MCP configuration, in VS Code | The MSSQL extension's Data API builder view |26| Per-entity MCP settings, descriptions and `anonymous`/`authenticated` permissions, in VS Code | The MSSQL extension's Data API builder designer |27| Hosting it in Azure, `runtime.mcp.allowed-hosts`, replicas, health | `deploy-dab-to-azure` |28| The identity DAB uses to reach the database | `entra-id-auth` |2930This skill owns the hosted endpoint: the client, its credential and role selection, the settings the31designer does not set, and proving what the agent can reach.3233## What the endpoint is3435- `POST /mcp`, Streamable HTTP, protocol version `2025-06-18`. `serverInfo.name` is36 `SQL MCP Server`. Clients send `Accept: application/json, text/event-stream`; replies arrive as37 `event: message` frames. A browser opening `/mcp` sees an error; that is not a fault.38- `initialize` returns an `Mcp-Session-Id` header. Every later request carries it. The session39 lives in the process that issued it.40- Seven tools, the same list for every caller. Their configuration keys under41 `runtime.mcp.dml-tools` name them: `describe-entities`, `read-records`, `create-record`,42 `update-record`, `delete-record`, `execute-entity`, `aggregate-records`; clients show the same43 names with underscores. There is no free-form SQL and no schema change. Stored procedures run44 through the execute tool, or as named tools of their own.45- `runtime.mcp.description` is returned to the client as `instructions` at `initialize`. It is the46 only text that tells the agent what this server is for; see47 [Tell the agent what this server is for](#tell-the-agent-what-this-server-is-for).48- `dab start --mcp-stdio role:<role>` is for local clients only. It uses the development49 `Simulator` provider and never reaches a hosted endpoint. Over stdio, 2.1.5 sends the50 description only as `serverInfo.description`, a human-readable field, with no `instructions`,51 when the client negotiates protocol `2025-11-25`, so a local client may never give it to the52 model.5354## Four things that fail while looking fine5556Each observed on 2.1.5 when this skill was written, with an entity granted only to `authenticated`.57To the user they are documentation, not something you measured: say so, and name what you did not run.58591. **`tools/list` is not a permission check.** An anonymous caller was offered all seven tools,60 including the delete tool, for a configuration in which it could do nothing.612. **The entity-description tool said `NoEntitiesConfigured` when the configuration had62 entities.** The caller's role could see none of them. The request reached DAB as a role with63 nothing granted: usually no `Authorization` header arrived, so it ran as `anonymous`, or the64 entities are granted to a named role and the client sent no `X-MS-API-ROLE`, so it ran as65 `authenticated`, which inherits from `anonymous` and never from a named role. Do not add66 `anonymous` permissions to make the message go away.673. **A denied tool call is HTTP 200.** A call to the read tool for a role without `read` returned68 200 with a tool result whose `status` is `error` and `type` is `PermissionDenied`. Monitoring69 HTTP status alone sees success. Read the result.704. **`Session not found` (-32001) is HTTP 404 from another process.** A replica that did not issue71 the session, a restarted container or a new revision all answer this way. The client must call72 `initialize` again. Scaling belongs to `deploy-dab-to-azure`.7374A 403 whose body names the `Host` or `Origin` header is the 2.1 host allowlist, not a permission.75`deploy-dab-to-azure` fixes it in the configuration.7677## Choose inbound authentication the client can actually perform7879The client's credential decides the DAB role for every tool call. The database never sees the80caller: DAB connects with its own identity for every request.8182| What the client can send | DAB provider | Consequence |83|---|---|---|84| A Microsoft Entra bearer token for the API | `EntraID`, with the token's `aud` and `iss` | `authenticated`, or a named role when the client also sends `X-MS-API-ROLE` and the token carries that role |85| Nothing | `Unauthenticated` | Every call is `anonymous`; grant `anonymous` only narrow `read` |86| An API key or another scheme | Put Azure API Management in front, which authenticates and forwards | DAB sees what the gateway forwards |8788One DAB instance has one inbound scheme. Two clients that need different schemes need two89instances. A client that cannot set custom headers cannot select a named role, so design its access90around `authenticated`.9192## Configure the client9394Visual Studio Code, `.vscode/mcp.json`. The token is prompted for, never written to the file:9596```json97{98 "inputs": [99 { "type": "promptString", "id": "dab-token", "description": "Access token for the Data API builder API", "password": true }100 ],101 "servers": {102 "sql-mcp": {103 "type": "http",104 "url": "https://<host>/mcp",105 "headers": { "Authorization": "Bearer ${input:dab-token}", "X-MS-API-ROLE": "<role>" }106 }107 }108}109```110111Drop `X-MS-API-ROLE` to run as `authenticated`. VS Code does not forward servers that need112`${input:...}` to Copilot harness sessions; there, use the portable `.mcp.json` with a top-level113`mcpServers` object and `"Authorization": "Bearer ${DAB_TOKEN}"` read from the environment.114115A pasted access token expires within hours. Use it to test. For a lasting connection, use a client116that obtains tokens itself, such as a Foundry agent's Microsoft Entra authentication mode, or a117gateway.118119**Foundry agent.** Add a tool, choose Custom, then Model Context Protocol, and enter120`https://<host>/mcp` as the remote endpoint. The authentication mode chosen there must match the121DAB provider; Unauthenticated in Foundry reaches only `anonymous` permissions.122123**MCP Inspector**, for debugging only:124`npx -y @modelcontextprotocol/inspector@2.12.0 https://<host>/mcp` (pin the release you have125reviewed), then add the `Authorization` header in its connection settings. Do not host Inspector126where others can reach it.127128## Tell the agent what this server is for129130Every Data API builder server offers the same seven generic tools. What this one holds, what it is131for and where it stops reach the agent through one setting, `runtime.mcp.description`, returned as132`instructions` at `initialize`. Entity and field descriptions say what a table or column means;133only this says what the server is for, and it is what lets an agent connected to several servers134pick this one for the right questions. Treat it as configuration, not as a comment.135136| Property | Consequence |137|---|---|138| One string, the same for every caller and role, returned before any permission is checked | Anonymous callers receive it too. No secrets, internal host or server names, or entities some role must not know exist |139| It restricts nothing | "Read-only" in the text stops no write; permissions do. Text that disagrees with the permissions misleads the agent |140| The client decides whether the model sees it | The MCP specification makes it a hint a client may add to the model's context. Check yours |141| Read once | DAB reads it at startup and a client receives it once per session: restart or redeploy, then reconnect |142| Blank or whitespace | No `instructions` field is sent |143144A useful description says, in a few sentences:1451461. **Purpose and audience**: what data this is, and which agent or task it serves.1472. **What is here**: the entities and custom tools the agent's role can reach, and what is148 deliberately not available.1493. **How the tools fit together**: list the entities before reading, filter and select columns150 instead of reading whole tables, aggregate for counts and totals.1514. **Limits**: read-only or not, units, currencies and time zones, freshness, and the questions it152 cannot answer.153154Leave out what each tool's own description already says, behaviour rules unrelated to this server,155and marketing.156157```text158Weak: Product catalog159Useful: Read-only access to Contoso's product catalog and order history, for the sales assistant160 answering customer questions about products, prices and past orders. Entities: Product,161 Order. Prices are USD; order dates are UTC. List the entities before reading, filter and162 select only the columns needed, and aggregate for counts and totals instead of reading163 every row. Inventory and customer contact details are not available here.164```165166**Review it whenever you create or review a configuration with MCP enabled:**1671681. Read `runtime.mcp.description` from the file and, for a hosted endpoint, the `instructions`169 that `initialize` returns.1702. It is missing if absent or blank. It is insufficient if it does not cover the four points171 above, or if it contradicts the permissions or the advertised tools.1723. Draft a replacement that opens with what the server is for, built from the configuration: the173 entities and actions the agent's role can reach, the advertised tools, custom tools, and174 entities kept out of MCP. Mark what the file cannot say, such as who the agent serves and what175 it must not be used for, as questions rather than guesses.1764. Present the current text beside the draft. Tell the user that every caller receives it at177 `initialize`, anonymous ones included, and that it restricts nothing. Ask them to confirm the178 purpose and answer the open questions, and wait for approval or edits before writing it.1795. Write it with `dab configure --runtime.mcp.description "<text>"`, set `runtime.health.roles`180 again afterwards (`deploy-dab-to-azure`), restart or redeploy, and confirm `initialize` returns181 the new text.182183## Shape what the agent sees184185Permissions are the control; tool switches only change what is advertised. Do both.186187In VS Code, make the per-entity settings below in the MSSQL extension's designer, which edits the188same file: descriptions, field and parameter descriptions, an entity's MCP switch, and a stored189procedure as a custom tool. The designer offers only `anonymous` and `authenticated` permissions190and no server-wide MCP settings, so named roles such as `agent`, the global tool switches and the191server description still go through the CLI, after the designer's edits.192193```bash194# read-only agent: grant read only, then stop advertising write tools195dab update Product --permissions "agent:read"196dab configure --runtime.mcp.dml-tools.create-record false \197 --runtime.mcp.dml-tools.update-record false --runtime.mcp.dml-tools.delete-record false198199# keep an entity on REST but out of MCP entirely (writes "mcp": false on the entity)200dab update AuditLog --mcp.dml-tools false201202# tell the agent what each entity and column means203dab update Product --description "One row per sellable product."204dab update Product --fields.name Price --fields.description "Unit price in USD."205206# a curated stored procedure as its own named tool207dab add GetTopProducts --source dbo.usp_GetTopProducts --source.type stored-procedure \208 --permissions "agent:execute" --mcp.custom-tool true \209 --description "Returns the best-selling products." \210 --parameters.name "top" --parameters.description "How many to return." --parameters.required true211```212213With MCP enabled, 2.1.5 `dab validate` warns when entities carry no `fields` definitions. Describe214at least the key and the columns an agent filters on. Any `dab configure` call above resets215`runtime.health.roles`; `deploy-dab-to-azure` covers the order.216217## Verify with requests, not with the client UI218219Run these against the hosted endpoint as the agent's own identity. Open220[references/mcp-requests.md](references/mcp-requests.md) when you send them; it has the full221bodies in bash and PowerShell.2222231. `initialize` returns 200, an `Mcp-Session-Id` header and `instructions` matching224 `runtime.mcp.description`. No `instructions` field means no description is set.2252. `notifications/initialized`, then `tools/list`, carrying the session header.2263. `tools/call` on the entity-description tool lists exactly the entities this role should see.2274. `tools/call` on the read tool with `{"entity": "<Entity>", "first": 1}` returns one record.2285. As a role that must not write, the create tool returns a tool error, not a record. Send this probe only to a229 disposable copy of the database: a permission wider than intended makes it a real insert. Against production,230 prove read-only from `dab configure --show-effective-permissions` and skip the probe.231232## When it fails233234| Symptom | Cause | Fix |235|---|---|---|236| 403 naming the `Host` or `Origin` header | Host allowlist | `deploy-dab-to-azure` |237| 401 | Token missing, expired, or `aud`/`iss` mismatch | Decode the token and compare with the configuration |238| `NoEntitiesConfigured` with entities configured | The caller's role sees none | Fix the token or `X-MS-API-ROLE`, not the permissions |239| Tool result `PermissionDenied` under HTTP 200 | The role lacks that action on that entity | `dab configure --show-effective-permissions` |240| 404 `Session not found` | Session issued by another process | Re-initialize; `deploy-dab-to-azure` for replicas |241| The agent picks the wrong entity or invents columns | No descriptions or `fields` | Add descriptions and fields as above |242| The agent ignores the server, uses it for questions it cannot answer, or reads whole tables | No `instructions`, or text without purpose, scope or limits | Write `runtime.mcp.description` as above |243244## Do not245246- Do not commit a token to `mcp.json` or `.mcp.json`.247- Do not treat `tools/list`, an HTTP 200 or a client's green status as proof of access.248- Do not grant `anonymous` to make the entity-description tool return something.249- Do not rely on disabling a tool, or on a description that says read-only, to stop writes; remove250 the permission.251- Do not leave `runtime.mcp.description` empty or generic, and do not put in it anything an252 anonymous caller must not see. Do not rewrite it without the user's approval.253- Do not probe write denial against a production database. A probe that is not denied is a write.254- Do not state the 2.1.5 behaviours above as timeless facts, and do not call them measured, verified or255 tested unless you sent the request yourself in this session. Attribute them as "documented for DAB 2.1.5256 in this skill, not verified against your endpoint", and keep the user's own transcript separate from them.