Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses irreversibility ('everything stored in it is destroyed and cannot be restored'), the required credential and its forwarding as a Bearer token, and stable-config guidance. It stops short of error/idempotency/rate-limit behavior, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The destructive nature and the not-sign-out distinction are front-loaded, which is exactly the right ordering. It is slightly over-long: the 'Source: POST /api/v1/sessions/revoke' line and the closing config-preference sentence are useful but push length beyond the essential warning plus routing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, so the description must cover behavior itself — and it covers the critical parts: irreversibility, auth, alternatives, and when the action is warranted. Missing coverage of failure modes and host/config plumbing keeps it short of complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does for the meaningful inputs: it explains that auth.sessionToken is forwarded as a Bearer token and recommends connection.workspaceName/connection.appId over dynamically generated identity fields. The remaining body/query/params are empty objects, but 'host' is not addressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Permanently revokes the session') and an exact scope ('referenced by the internal SESSION Bearer token'), then explicitly distinguishes itself from sign-out and names the sibling endpoints (POST /api/v1/auth/logout, GET redirect helper). An agent can tell this apart from post_auth_logout and the sibling post_sessions_revoke_session_id without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives both when-to-use ('only when the user or an admin deliberately wants the session and its data deleted, for example on account deletion') and when-not ('This is NOT sign-out: to sign a user out and keep their data, use ...'), naming concrete alternatives. Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.