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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds substantive behavior the annotations don't: the held amount is released in full and cancellation is impossible once generation has begun, which tells the agent exactly what state change and failure mode to expect.

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?

Two short sentences, zero filler, with the action and side effect front-loaded and the exclusion immediately following. Every clause carries information the agent needs.

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 destructive tool with full schema coverage and an output schema, the description covers purpose, side effect, and the failure condition. Only the exact error response for a non-queued job is unstated, a minor gap given the output schema exists.

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% and the single parameter is documented as 'job_id returned by generate'. The description adds no further meaning about the identifier, so the baseline 3 applies.

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 gives a specific verb and resource ('Cancel a job') plus a scope qualifier ('still queued') and the side effect ('release the held amount in full'). It clearly separates this tool from siblings like generate or check_job by stating exactly what state the job must be in.

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 states the precondition (job must still be queued) and the exclusion ('Jobs that already started generating cannot be canceled'), which is strong when/when-not guidance. It stops short of naming an alternative path for already-started jobs, so it isn't a full 5.

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