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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description is not obligated to establish danger. It still adds real value: revocation is immediate ('at once') and the effect is behavioral (the calling system is 'refused from then on'), plus an authorization constraint ('Owner only') that annotations do not cover. It omits whether revocation is reversible.

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?

Two short clauses, front-loaded with the effect and followed by the permission constraint. No filler and nothing buried.

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?

For a one-parameter destructive tool with a safety annotation and no output schema, the description covers effect, timing and authorization. The remaining gaps are minor: whether the action can be undone, and that the id should be sourced from list_api_keys.

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?

Single required parameter with 100% schema coverage, so the schema already carries the semantics. The description adds nothing about the id (format, where to find it, whether it is the key token or an internal identifier), so the structured data does all the work.

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 and resource: stop one API key working, immediately. That distinguishes it from sibling list_api_keys and from unrelated mutation tools like disconnect_app. It falls short of a 5 only because it never names the read-side sibling an agent would use to find the id.

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?

'Owner only' gives one precondition, but there is no explicit guidance on when to revoke versus other removal actions, and no pointer to list_api_keys for obtaining an id. Usage is implied rather than stated.

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