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

No annotations are provided, so the description carries the full burden of disclosing behavior. It states the destructive nature of the action ('Revoke'), the soft-revoke distinction via delayDays, and the Bearer authentication requirement. It does not mention error behavior or idempotence, but the key side effects are clearly disclosed.

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 two short sentences that front-load the core purpose before adding the delay nuance and auth requirement. There is no wasted wording; every clause earns its place.

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 two-parameter mutation with no output schema and no annotations, the description covers the essentials: what is revoked, how to defer revocation, and what authentication is required. It does not state the return value or how to locate the token beforehand, but those are minor gaps for a straightforward revoke operation.

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 schema leaves 'token' as a bare string, so the description adds meaning by calling it a 'guest share token.' For delayDays, it adds the valid range (1–365) and the 'soft revoke' concept beyond the schema's existing description. This compensates well for the 50% schema description coverage.

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 opens with the exact action and object: 'Revoke a guest share token.' It is clearly distinct from the sibling tools, which create shares (share_fiche), list shares (list_shares), and delete other resources (delete_fiche, delete_webhook). An agent can tell when this tool applies without needing to infer from the name alone.

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 does not explicitly state when to use this tool versus alternatives, nor does it give exclusions. The intended use is inferable from the phrase 'revoke a guest share token' and the sibling set, but there is no direct routing like 'use list_shares to find the token' or 'use delete_fiche to remove the entire fiche instead.'

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