取消 GPT 图片任务

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

Adds substantive semantics beyond the annotations: the cancellation is local-only, upstream execution may continue, no refund is guaranteed, and no retry is triggered. That is exactly the caveat an agent needs before a non-idempotent cancel; it only omits what happens if the job is already finished or unknown.

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?

One compact statement with the action front-loaded, then three semicolon-separated caveats. No filler at all; every clause carries a distinct constraint.

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, no-output-schema tool, the behavioral caveats cover most of what matters. The remaining gap is the identity of job_id, which the description should have sourced given the schema's zero coverage.

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 single required parameter job_id has 0% schema description coverage, so the schema supplies only 'string, minLength 1'. The description never mentions job_id, its format, or where to obtain it (e.g., from generate_gpt_image or get_image_job), leaving the parameter undocumented.

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?

Clear verb+resource: cancels a queued or running *local* image job, with the 'local' qualifier precisely scoping what is cancelled. It is distinguishable from siblings (get_image_job reads, generate_gpt_image creates) without naming them, but it makes no explicit sibling callout.

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 description says what state a job must be in (queued or executing) to be a valid target, which implies when to call it. It does not state when not to use it, nor whether one should first verify status via get_image_job.

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