Muse 依圖改圖

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 that local paths are auto-encoded to base64 (caller needn't handle it), that results are written to disk and an absolute path is returned, and that each image costs US$0.01. Missing only failure behavior and any auth/rate-limit context.

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?

Four tightly packed sentences, each earning its place: purpose, input handling, output location, and cost. The purpose is front-loaded and no sentence is redundant.

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 nine-parameter tool with a nested extra_params object and no output schema, the description covers the essentials: what it produces, where output goes, and cost. It does not address error handling or synchronous-vs-async behavior, but the rich schema fills most parameter detail.

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 100%, so the schema already documents all nine parameters, establishing a baseline of 3. The description reinforces the images parameter (local path or URL with automatic base64 conversion), but this largely overlaps the schema rather than adding new meaning.

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: generate a new image from an existing image plus a prompt using the Meta Muse model. This implicitly separates it from generate_image (which presumably starts from scratch), but it never names or contrasts with siblings such as iterate_image, leaving that distinction to inference.

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?

It implies you use this when an existing image exists ('依既有圖片'), but offers no explicit when-to-use guidance and no routing between edit_image, iterate_image, and generate_image. An agent must guess which sibling to pick for a given modification workflow.

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