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

Adds meaningful behavior beyond annotations: the 422 no-op-reject on already-terminal jobs, best-effort box reaping, and 'cancel never meters' (no billing impact). This is rich context that isn't derivable from the annotations. Annotations already cover idempotency and non-destructiveness.

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 dense sentences, front-loaded with the core action and scope. The parenthetical job-type list and the TTL/metering details are useful, though the sentence is somewhat packed. 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 single-param mutation tool with no output schema, the description covers the why, the scope, the billing behavior, and the terminal-state edge case. It omits auth/permission requirements and the response shape, but is largely complete.

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% (jobId is documented). The description adds that the jobId is the one 'returned by an enqueue call', giving provenance, but no format details. Baseline 3 is appropriate when the schema carries the parameter documentation.

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+resource ('Cancel a running async job') and enumerates the job types it applies to (verify / preview / brand-kit-extract). It distinguishes itself from siblings like cancel_compose/cancel_render/cancel_export by targeting the generic async job returned from an enqueue call, and from wait_job.

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?

Gives a clear motivating scenario ('abort a mis-priced job instead of waiting out its TTL'), which implicitly contrasts with wait_job. However it doesn't explicitly name wait_job as the alternative or state when not to cancel (e.g., terminal jobs), leaving some inference.

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