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

The description goes beyond the annotations by explaining important side effects: failed/incomplete provider work is refunded automatically, and for waiting-for-approval jobs, reusable 360 and pose charges are retained. This is genuinely useful behavioral context that annotations like destructiveHint:false do not capture. No contradiction between the description and annotations is present.

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 concise and front-loaded, beginning with the essence 'Abort a running job.' Every sentence adds information: cost, refund rules, approval-specific behavior, and usage guidance. There is no fluff or repetition.

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 tool with no output schema and existing annotations, the description provides all needed context: the core action, the specific cancellation timing, refund behavior, charge retention specific cases, and a usage recommendation. An agent can invoke this tool correctly without further information.

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 provides a clear description for jobId ('Job id to cancel.'), and coverage is 100%. The description adds no extra semantic meaning for the parameter beyond the basic one, so the baseline score of 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 states the verb 'Abort' and the resource 'a running job', making the tool's purpose explicit. The wording distinguishes it from siblings like get_job or retry_job, since those do not abort a running generation. The phrase 'FREE' also adds a useful top-level qualifier.

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 gives a clear when-to-use condition: 'Use this when a generation is clearly going wrong rather than letting it run to completion.' This is explicit context, but it does not name a specific alternative tool such as retry_job, nor does it state when cancellation would be the wrong choice. That prevents a full score of 5.

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