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

Annotations already indicate destructiveHint=true, but the description adds crucial behavioral details: it frees a device slot, the device loses access on the next license refresh, and it is not idempotent—unknown or already-revoked ids fail with not_found. This explains side effects and error semantics beyond the annotations.

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 well-structured: it leads with the core action, then explains the effect, then clarifies non-idempotency and error behavior, and ends with the return value. Every sentence adds value; there is no fluff. The length is justified by the need to clarify the non-idempotent and error behavior.

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?

With a single parameter and no output schema, the description fully covers what the agent needs: it states the parameter source, the effect, the error condition, and the return value. The agent can confidently invoke this tool without further context.

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 already describes the parameter as 'Device registration id from list_devices.' with 100% coverage, so baseline is 3. The description reinforces this by saying 'find ids with list_devices' and explains that an unknown id fails, which adds context about valid values and error handling, going slightly beyond the 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 verb 'revoke' and the resource 'registered device' by registration_id, and distinguishes it from a delete operation. It also mentions freeing a device slot, which clarifies the purpose beyond just revoking access.

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 explicitly tells the agent to find ids with list_devices, and clarifies when it is not appropriate: it is not idempotent and unknown ids fail with not_found. This implicitly routes the agent to use list_devices for discovery and warns against expecting a no-op. It also differentiates from a delete operation.

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