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

Annotations declare non-read-only, open-world, non-idempotent but non-destructive, and the description adds real context on top: site credits starting at 30 per image on the default model, a separate USD wallet for API keys, and the quote-then-confirm gate. It does not say whether the call returns a quote object or an async job, which would close the loop.

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 purpose before billing mechanics, with no filler. The billing sentence is dense and packs two payment paths plus a two-step confirmation into one line, which is efficient but slightly overloaded.

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 6-parameter, nested-object tool with full schema coverage and no output schema, the description covers purpose, cost model, and the approval prerequisite an agent needs before invoking. The main gap is the return shape — the description implies a quote is returned if unapproved but never says what an approved call yields.

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 parameter documentation is already baseline-adequate. The description still adds value beyond the schema by tying max_credits to the OAuth path, currency/max_usd to API keys, and explaining the quote-confirm sequencing — though it doesn't clarify the image vs image_url split (left entirely to the schema).

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 concrete transformation verb ('Show the same scene or subject from a different viewpoint'), which is more specific than the title and clearly distinct from sibling transforms like change_pose or relight_photo. It never names a sibling or states the boundary, so the differentiation is implied rather than 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 a procedural rule for the two-step approval flow ('Omit approval to get a quote, then confirm max_credits...'), which is genuine usage guidance for how to call it. However, it says nothing about when to pick this over change_pose / edit_image / create_image, or what input is required (a source image), leaving the main selection decision to inference.

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