通过 Responses 生成图片

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the mutation and external-dependency profile is partly carried structurally. The description adds useful context that the call runs through the OpenAI Responses API and can be chained via previous_response_id, but it never mentions that results can be written to disk (output_path/overwrite), says nothing about latency, cost, or failure behavior for this remote call. No contradiction with annotations.

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?

A single front-loaded sentence that states the mechanism (Responses API image_generation) first, then the differentiating capabilities. No filler, no repetition of the tool name, nothing 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?

An output schema exists, so return-value explanation is correctly omitted, and the rich schema covers most operational detail. But for a 13-parameter tool with sibling confusion, the description leaves two material gaps: how this differs from generate_image/edit_image, and that the call can persist files to disk. Adequate, not complete.

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 77%, so the schema already explains most fields, but two parameters carry no schema description at all: previous_response_id and the action enum. The description supplies real semantics for the first of these ('多轮编辑'), and '参考图输入' clarifies the role of the images array beyond its format description. That is genuine added meaning rather than restatement.

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 name and title state a specific verb and resource (generate images via the OpenAI Responses API image_generation tool), and the description adds the two capabilities that define this particular variant: previous_response_id-driven multi-turn editing and reference-image input. However, it never names its siblings generate_image and edit_image, so an agent cannot tell from the description alone which of the three to pick.

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?

Mentioning 'supports previous_response_id multi-turn editing and reference image input' implies the selection condition (use this when continuing an existing image conversation or supplying reference images), but the guidance is never made explicit. There is no statement of when NOT to use it and no reference to generate_image or edit_image as alternatives, leaving the routing decision to inference.

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