Edit with multiple references

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

Annotations only declare the general write/non-idempotent profile, so the description adds real value: the ordering contract ('refer to them as image 1, image 2, ... in the prompt') and the default output sizing rule ('follows image 1's aspect ratio unless width/height or aspect_ratio are given'). It does not cover file-safety behavior on output (non-overwrite, project-scoped paths), though the schema does.

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 action, followed by the two rules an agent would otherwise get wrong (ordering and default aspect ratio). The only mild redundancy is '(up to 10)', which the schema's maxItems already states.

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 9-parameter generation tool with no output schema, the description supplies the key invocation semantics and the include_preview parameter hints at the return shape, but it never states what a successful call yields (image path/list) or that generation is nondeterministic unless seed is set. The remaining gap is small given the strong schema coverage.

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 78%, so the schema already carries most parameter meaning (seed, quality, output_path, aspect_ratio are all documented inline). The description goes beyond it by explaining parameter interaction: reference order maps to 'image 1, image 2' labels in the prompt, and width/height/aspect_ratio override the inherited image-1 aspect ratio.

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 states a specific verb+resource ('Create an image from several reference images ... and an instruction'), which clearly separates it from the singular sibling edit_image by emphasizing multiple ordered references. It stops short of naming or contrasting any sibling explicitly, so an agent must infer the boundary from the 'several reference images' phrasing.

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?

Usage is implied rather than stated: the multi-reference, instruction-driven framing suggests when this beats generate_image or edit_image, but there is no explicit when-to-use/when-not-to-use rule or named alternative. Guidance is adequate but left to inference given seven siblings that overlap in the image-editing space.

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