subject_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 missing-subject failure path, the 1024 dimension cap, that unspecified seed/steps/guidance fall back to engine defaults, and the slower-but-finer tradeoff of more steps. It does not cover output file format, overwrite behavior, or reproducibility guarantees, so it falls short of 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?

Purpose and the sibling warning are front-loaded in the first two lines, followed by a clean parameter block. Every sentence earns its place — the dress/face example in particular prevents a common misuse without padding.

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 the return value needs no elaboration beyond the one-line note that it yields a local path. Across a 7-parameter, 2-required generation tool, the description covers invocation, prerequisites, dimension limits, optional-parameter defaults, and identity/scene separation — nothing an agent needs is missing.

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 all seven parameters. Critically it adds semantics the schema cannot: scene controls action/place/angle only while identity comes from the dated 定妆 image, and clothing can be swapped via scene text ('wearing heavy red armor') while preserving the face. That is genuine meaning beyond the schema.

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?

Specific verb+resource (出一张新图 of a 已定妆 character/object) plus the scope constraint that appearance must stay consistent with every prior image. It is immediately distinguishable from the sibling generate_image. No ambiguity about what the tool produces.

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?

Explicitly routes the agent: use this for game assets 不要用 generate_image, with the reason (generate_image mutates the face each time). It also states the prerequisite path — if subject doesn't exist, go to create_character/create_animal/create_object first. Both when-to-use and the alternative are named.

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