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

Annotations only declare non-read-only, open-world, non-idempotent. The description adds real behavioral context the annotations don't carry: credit pricing from 30 credits/image, a separate USD wallet for API keys, and a quote-then-confirm two-step approval flow. It omits whether the call is async or returns a job handle for polling.

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?

Three sentences, front-loaded with the core operation before the billing detail. The final sentence is dense but each clause (quote, max_credits, currency/max_usd) maps to a distinct action, so little is wasted.

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 7-parameter, nested-object, open-world generation tool with no output schema, the description covers the hardest part (billing approval) well but says nothing about what comes back — presumably a job to poll via get_job — or whether the call is asynchronous. That is a meaningful gap given the absence of an output schema.

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 100%, so every parameter, including the nested image object and the max_credits/max_usd distinction, is already documented in the schema. The description restates the OAuth vs API-key approval parameters but adds no syntax or constraint beyond what the schema says (e.g. 'Never convert max_credits'). Baseline 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?

States a specific verb and resource — 'Re-pose the person in a photo to match the pose in another picture' — which is concrete enough to separate it from near neighbors like change_camera_angle, copy_motion, and relight_photo. The two-input structure (subject photo + pose reference) is made explicit.

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?

Gives clear procedural guidance for the billing path: omit approval to get a quote, then confirm max_credits (OAuth) or currency/max_usd (API keys). It does not address when to choose this over a sibling such as copy_motion, but the context for invoking it correctly is present.

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