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

Adds substantial context beyond the annotations: held credits are refunded, already-running jobs fail with 409, the canceled job is returned, and the call is free. This complements destructiveHint and idempotentHint without contradicting them.

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 key action and refund behavior are front-loaded, followed by the running-job exception, return value, and cost. Every sentence adds useful information with 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 cancellation tool with rich annotations and no output schema, the description covers eligibility, failure behavior, return value, and cost. Nothing essential for correct invocation 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 already documents the single id parameter clearly at 100% coverage, including that it is the id returned by a generation call. The description does not add further parameter semantics beyond what the schema provides, so the baseline 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?

States a specific verb and resource: cancel a queued job started through the API or MCP. It also distinguishes cancellable queued jobs from already-running jobs, which an agent needs in order to select it correctly.

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?

Clearly says to use this for queued jobs and that running jobs cannot be canceled because they return 409. It does not explicitly name getApiJob as the way to check job status first, so it falls short of full when/when-not/alternatives guidance.

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