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

Annotations only declare destructiveHint=false and openWorldHint=false; the description carries the important behavior itself: the secret is returned once and never again, keys never expire, and ending access requires explicit revocation. It also adds a human-confirmation requirement, which is exactly the kind of operational context annotations cannot express.

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?

Four short sentences with the most consequential facts (impersonation, one-time secret, no expiry) front-loaded and nothing wasted. The confirmation instruction lands last, which is a slightly weaker position than placing the gating requirement first, but the text is otherwise tight.

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 credential-issuing mutation with no output schema, the definition covers everything an agent needs: what it creates, how privileged it is, that the secret appears only in this response, that there is no expiry, and how to undo it. The one-time-secret warning in particular closes the gap left by the absent output schema.

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 100%, so every parameter including label, purpose, scopes, and user_id is already documented in the schema, and the description only echoes the scopes ceiling that the schema also states. It adds no new meaning about parameter formats or defaults, so the baseline 3 applies.

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 ("Issues an API key") plus the crucial semantic that the key acts as the named person and its scopes are bounded by the caller's own privileges. The closing clause "revoke one to end it" implicitly routes to desk_revoke_api_key, so an agent can place it among the desk_*api_key siblings 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 a real precondition ("Confirm with the user first") and a hard constraint (scopes never exceed the caller's), which shapes when and how to call it. It does not explicitly name alternatives (desk_list_api_keys to audit, desk_revoke_api_key to undo, desk_list_api_key_people for user_id), so usage routing is clear but not fully spelled out.

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