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

Annotations already declare destructiveHint=true, and the description adds meaningful behavioral context: the same id is revoked, the old secret returns 401 invalid_api_key, and X-API-Key is an alias. It also explicitly states 'No ops file-edit,' which is a useful exclusion. This goes beyond the annotations without contradicting them.

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 description is compact and front-loaded with the core action ('Invalidate the presented secret'). The additional details about 401 behavior and header preference are valuable and concise. The title's trailing 'image ocr, ocr text, vision text' is noise, but the description itself is well-structured.

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 zero-parameter destructive tool, the description covers the essential context: what happens, the error code, and the authentication mechanism. It lacks an explicit warning about irreversibility, but the destructiveHint annotation and 'Invalidate' convey that. The 'No ops file-edit' note adds clarity about scope.

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?

The input schema has zero parameters, so the description doesn't need to explain parameters. The description instead clarifies that the secret is 'presented' via the request context (Authorization header or X-API-Key), which is essential for an agent to understand how the tool knows which key to revoke. This compensates for the empty schema.

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?

The description clearly states the tool invalidates the presented secret and references the POST /keys/revoke endpoint. It distinguishes itself from siblings by noting it revokes the same id, while rotate_key likely issues a new secret. However, the title's trailing 'image ocr, ocr text, vision text' is confusing and unrelated to the described behavior.

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?

The description provides explicit guidance on authentication preference: 'Prefer Authorization: Bearer; X-API-Key is an alias only.' It also clarifies the effect (old secret fails 401) and notes 'No ops file-edit,' which helps an agent understand what this tool does not do. It does not explicitly name alternatives like rotate_key, but the context is sufficient.

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