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

The description discloses key behaviors: it spends credits (cost implication) and returns a job id for polling (asynchronous). It also clarifies the idempotency semantics in the parameter description. These are important behavioral traits beyond the annotations, which only indicate non-read-only and non-destructive. It could mention failure modes or whether it modifies the character, but current disclosure is strong.

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: it states the action, the object, the cost, and the next step in a single sentence. The parameter descriptions add necessary detail without bloat. No redundant information.

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?

Given the tool's complexity (5 parameters, asynchronous behavior, credit cost, idempotency), the description covers the essential context: what it does, cost, and follow-up action. It doesn't describe the output format beyond 'job id', but since there is no output schema and the sibling tool get_job exists, the information is sufficient. It could mention whether the job result is an image asset, but that's inferable from the tool name.

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 description coverage is 100%, so the baseline is 3. The description adds value by explaining the idempotency key behavior (reuse vs new) and the 'defaults to the base look' semantics for character_look_id. It doesn't further explain reference_image_asset_ids beyond the schema, but the schema already says 'Existing asset ids to use as references.' The added context about idempotency and look defaults raises the score.

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 the tool's purpose: generating a reference image for a character. It is distinguished from sibling tools like generate_location_image and generate_shot_background_image by explicitly mentioning 'for a character', and from get_character/get_character_looks by indicating it generates (creates) rather than retrieves.

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 provides clear usage context: it creates a character reference image, spends credits, and returns a job id to poll. It implies asynchronous usage via 'poll it with get_job'. It doesn't explicitly contrast with alternative tools like generate_character_look or say when not to use it, but the sibling list makes the distinction reasonably clear.

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