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

The annotations already indicate destructive behavior, non-read-only, and idempotent semantics. The description adds meaningful context: the token becomes invalid immediately, login is required, and the return value 'revoked' indicates whether an actual revocation occurred. These details go beyond the annotations and help the agent anticipate side effects.

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 every clause earns its place: login requirement, operation and effect, prerequisite workflow, and return-value semantics. It is front-loaded with the most critical gate ('需要登录') and avoids any filler.

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 single-parameter tool with no output schema, this description provides everything an agent needs to invoke it correctly: authentication requirement, how to acquire the parameter, what the operation does, and what the response means. No critical information is 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?

The schema covers 100% of the parameter with a minimal description ('设备 id'), while the tool description adds important semantic guidance: the deviceId should come from list_my_devices. This provenance information is genuinely useful for correctly populating the parameter, raising it above the baseline.

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 uses a specific verb ('吊销'/revoke), names the resource ('当前用户的某台接入设备'), and states the effect ('token 立即失效'). It clearly distinguishes this tool from siblings by scoping it to the current user's own device and explicitly referencing list_my_devices as the way to obtain the deviceId.

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 says it requires login and instructs the agent to first call list_my_devices to obtain a deviceId, which is a clear workflow guideline. It does not mention exclusions or alternative tools explicitly, but the usage context is unambiguous: revoke one of the current user's devices.

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