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

The description adds meaningful behavioral context beyond the annotations by warning that credits are spent and that the tool returns a job id rather than a direct result. It does not contradict the readOnlyHint or destructiveHint annotations.

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 two short sentences with no redundant wording. It efficiently conveys purpose, side effect, and polling behavior.

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 tool with no output schema, the description adequately explains the return type (job id) and the follow-up action (poll with get_job). It is slightly thin on optional inputs, but overall the agent has enough context to invoke it correctly.

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?

Required parameters such as shot_id, short_shot_number, and idempotency_key are described in the schema, and the idempotency_key description is thorough. However, the tool description itself adds no parameter-specific meaning, and reference_image_asset_ids has no schema description or clarification.

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 clearly states a specific action ('Generate an empty background plate') for a specific resource ('one short shot'), and the mention of spending credits and returning a job id distinguishes it from sibling generation tools like generate_shot_clip.

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?

It explicitly notes that credits are spent and that the result is an asynchronous job id to poll with get_job, giving the agent clear next steps. It does not explicitly contrast with alternatives, but the 'empty background plate' scope is enough for most use cases.

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