import_subject

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

With no annotations the description carries the full burden, and it delivers real behavioral detail: images over 1024 are downscaled, alpha channels are converted to RGB (transparency becomes black), and force overwrites an existing subject. It also warns that a scene-containing reference will replicate that scene. Missing permission/auth or failure-mode disclosure 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-loaded with the one-line purpose before dropping into a structured 参数 list, and each parameter note earns its place with actionable detail. Slightly long, but the length is justified by the 0% schema coverage it has to make up for.

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 mutation tool with no annotations, the description covers overwrite semantics, image preprocessing, and reference-image constraints; the existence of an output schema means return values need not be explained. Auth/permission requirements and error behavior remain unstated.

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 documents every one of the five parameters: name (used later by subject_image), image_path (with concrete requirements: single subject, front or 3/4 view, clean background, fully visible), appearance (required, injected into every subsequent scene prompt, with a warning about drift if omitted), kind, and force.

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 action (import a ready-made image to define a subject's look) and explicitly distinguishes it from siblings: the result is identical to create_character/create_object, only the reference image is user-supplied. An agent can tell it apart from create_character without opening either 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?

Explains the workflow context clearly: use this when you already have a reference image, then subject_image generates arbitrary scene images whose appearance derives from that image. The comparison to create_character/create_object implicitly covers the alternative, though it never states an explicit when-not-to-use rule.

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