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

Goes well beyond the annotations: states that the price is charged (locked) at submit time, that jobs exceeding max_cost_usd are refused, that failed jobs are not charged, and that reference images must be public https URLs. The billing semantics — the most consequential behavior for a non-destructive but costly operation — are disclosed directly.

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?

Five short sentences, each carrying a distinct fact (charge, refusal, job_id, polling, failure billing, URL constraint) with no filler 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 paid async generation tool with an output schema, the description covers the missing pieces: charging model, failure handling, polling target, and URL validity. Nothing an agent needs in order to call it correctly is absent.

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 already 100%, so the baseline is 3; the description adds real meaning on top by explaining that max_cost_usd acts as a hard refusal threshold and that image URLs must be public https. It does not explain the model/template input variants, which the schema handles.

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?

Specific verb and resource: 'Start a video or image generation job and charge the locked price from the balance.' An agent can distinguish it cleanly from check_job, cancel_job, estimate_cost and list_models without opening a schema.

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?

Explicitly routes the agent to check_job for results and states the max_cost_usd refusal condition, which effectively tells the caller when the job will not run. It does not say whether estimate_cost should be called first or how to pick a model, but the core workflow is clear.

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