create_image_to_image_task

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

No annotations exist, so the description carries the full burden, and it delivers real behavioral detail: per-model allowed aspect ratios, the default '1:1', the mutual-exclusion rule, and that remove_background yields a transparent RGBA PNG. It omits the async task model (that a task id is returned and must be polled with retrieve_image_to_image_task) and any auth/cost constraints, which is the main remaining gap.

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?

It is front-loaded with the core action and then walks parameters in a logical order with no filler sentences. It runs as one dense block rather than a structured list, which costs a little readability on first parse but nothing 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 6-parameter creation tool with no output schema and no annotations, the description covers inputs, constraints, defaults, and one output-format nuance (RGBA PNG). What is missing is the task lifecycle — that this enqueues work and must be polled via retrieve_image_to_image_task — which matters given the create/retrieve/list/stream family.

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?

With 0% schema description coverage the description must do all the work, and it does: it enumerates the ai_model values, constrains reference_image_urls to 1–5 public URLs or base64 data URIs, and gives valid aspect_ratio values per model family with a stated default. Every parameter is given meaning beyond its bare type.

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 ('Generate a new image') and adds the defining scope clause 'based on reference images and a text prompt', which is exactly what separates it from the sibling create_text_to_image_task. An agent can pick it out of a 50-tool list without opening the 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?

The required reference_image_urls plus 'prompt describes the transformation' makes the use case (image-to-image editing/restyling) clear, and it states a hard exclusion: 'Cannot combine aspect_ratio with generate_multi_view'. It does not name an alternative sibling or spell out when NOT to use it, so it falls short of a 5.

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