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

Annotations already declare destructiveHint, idempotentHint=false, and readOnlyHint=false, so the safety profile is known. The description adds real value beyond them: Gems consumed are not refunded (a cost consequence) and cancelling a cancelled request is a no-op (concrete idempotency semantics). It stops short of saying what the response contains or whether the request transitions through an intermediate state.

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?

Three short sentences, front-loaded with the action, each carrying a distinct constraint or consequence. No 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 one-parameter mutation with no output schema, it covers the cost side effect and the edge cases that matter. A brief note on what the call returns (e.g. updated request status) would close the remaining gap.

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?

Single parameter with 100% schema coverage and its own description tying it to generate's return value, so the schema does the heavy lifting. The tool description adds nothing about request_id format or validation, which is acceptable at this coverage level.

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?

States a specific verb (stop/cancel) and resource (a queued or running request), and ties the resource back to its origin tool, generate. The scope qualifier 'queued or running' distinguishes it cleanly from get_request, list_history, and generate.

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?

Explicitly gives the use condition (request is queued or running) and the exclusion (a finished request cannot be cancelled), plus the no-op case for an already-cancelled request. An agent can decide whether to call this without inferring anything from siblings.

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