generate_image

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

With no annotations, the description carries the full burden and does well: it discloses the non-deterministic/one-off nature of the output, that reference_image_path switches to image-to-image mode, and the speed/quality tradeoffs of num_inference_steps and guidance_scale. It stops short of covering permission needs, rate limits, cost, or resolution failure modes, which keeps it from a 5.

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?

Front-loads the defining distinction, then the sibling routing, then a compact parameter list, then the return value. Given the 0% schema coverage the parameter section is earned, and there is no filler.

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?

Despite having no annotations and a 7-param schema with no descriptions, the definition covers scope, alternatives, per-parameter semantics, and even the return value (a local path). An output schema exists, so return details are not strictly required, making this fully sufficient for correct invocation.

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 0%, so the description must compensate and it does: every one of the 7 parameters is explained with meaning beyond type, including the 1024 cap on width/height, the optional seed, the img2img behavior triggered by reference_image_path, and the quality/latency and adherence/artifact tradeoffs of the two sampling params.

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 (生成一张一次性图片) and immediately defines the key scope constraint: the output is not guaranteed consistent with any other image. It explicitly distinguishes itself from create_character, create_object, and subject_image, so an agent can route correctly without opening any 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?

Gives both when-not and when-to-use: recurring characters/objects should go to create_character/create_object then subject_image, while this tool is for backgrounds, UI base images, and other one-off assets. The alternative is named with the condition that selects it, leaving nothing to inference.

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