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

The annotations already flag destructive=true, idempotent=true and openWorldHint=true, yet the description adds substantial detail: a queued bounce has its budget refunded, the result of a mid-render bounce is dropped on arrival, a running conversion cannot be stopped and its output is discarded, and credits are refunded only when the conversion itself fails. It also documents the terminal-state error path (409 already_terminal), which is exactly the post-conditions an agent needs before committing a destructive action.

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 core action, then splits the caveats by job type in a compact label-colon format, then ends with the error case. Every clause carries information; there is no filler or restatement of the title.

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, but the description compensates by describing the observable outcomes per job type and the 409 already_terminal response. Combined with annotations covering the safety profile and a fully documented single parameter, an agent has everything needed to call it correctly.

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 tool has a single required parameter with 100% schema coverage, and the schema already lists where job_id comes from. The description adds nothing about the identifier itself, such as format or prefixes, so its value beyond the schema is only the surrounding context about job lifecycle rather than parameter meaning.

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 first sentence gives a specific verb plus resource and states the exact scope: 'Cancel a queued or running job.' The following sentences distinguish this from implied sibling actions by explaining that check/wait-style observation is not what happens here, and they break the outcome down by the kind of job being targeted (bounce_session vs convert_project).

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 definition explains usage in context: it states that it applies to queued OR running jobs, and it spells out per-job-type consequences so an agent can decide whether calling it is worth it, for example a conversion cannot be stopped mid-render, so the cancel only takes effect at the end. It does not explicitly say when NOT to use it, or point to an alternative such as doseedo_check_task or doseedo_wait_task, so it falls short of full alternative routing.

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