revoke_device

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

Beyond the annotations (destructive, idempotent, not read-only), the description discloses the timing of the effect ('loses access on its next license refresh'), the failure mode for unknown ids ('fails with not_found'), and the exact success return ('revoked: true with the registration_id'). This substantially exceeds what annotations alone provide and does not contradict 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 front-loaded with the verb and object, and each key fact appears early. The only flaw is redundancy: the instruction to use list_devices appears twice ('find ids with list_devices' and 'Use list_devices to find registration ids'), which could be trimmed without losing information.

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?

There is no output schema, so the description correctly explains the return value ('Returns revoked: true with the registration_id'). It also covers the prerequisite, the destructive lifecycle effect, and the error case, leaving nothing necessary for a correct call missing.

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 coverage is 100% (registration_id is described as 'Device registration id from list_devices'), so the baseline is 3. The description adds meaning by linking the parameter to the list_devices lookup and by spelling out the error behavior for an invalid registration_id, going beyond the schema field description.

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 a specific verb and resource: 'Revoke one registered device by registration_id.' It also clarifies the scope by mentioning the freeing of a device slot and pointing to list_devices, making it unmistakable that this is device revocation rather than the API-key or connector operations in the sibling list.

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?

It gives actionable guidance by telling the agent to use list_devices to find registration ids, both parenthetically and in the final sentence. It does not explicitly name alternative tools or when not to use this one, but none of the siblings perform device revocation, so the context is clear and the prerequisite is explicit.

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