p-pic

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

With no annotations provided, the description carries the full burden, and it delivers: it discloses the pipeline name, default model, default size, provider resolution order (EDIT_IMAGE_ADAPTER env → sensenova), and instance fallback behavior (None → main instance). This gives an agent a realistic picture of how invocation will behave. The only omission is output behavior, but an output schema is present, lowering that burden.

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?

The structure is efficient: a one-line purpose, a scannable parameter list, and a final note about the callable signature. The Python-syntax note about required-before-default parameters is unusual but earns its place by clarifying the exact tool contract. Nothing is redundant, though the signature line partially repeats schema information.

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 5-parameter tool with zero schema descriptions and no annotations, the description covers all parameters, defaults, and behavioral nuances, including the provider fallback and instance resolution. The reference to '见 3.7' for instance details is a minor external dependency, and the output schema covers return values. Slightly more context on when to set provider explicitly would round it out.

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 fully compensate, and it does. Every parameter gets a meaningful definition: prompt is the edit instruction, image_path specifies local path and accepted formats (PNG/JPG/WEBP/GIF), size has a default, provider enumerates the two backends, and instance explains the named-instance concept. This exceeds what a bare schema would convey.

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 opening line '图生图（EDIT_IMAGE 流水线，默认模型 sensenova-u1.5-lite）' identifies the tool as an image-to-image operation on the EDIT_IMAGE pipeline with a named default model. This is clear enough to distinguish it from siblings like r-pic (likely generate-from-reference) or g-pic (likely text-to-image), though it lacks an explicit action verb like 'edits' or 'generates'.

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?

No guidance is given on when to choose this tool over its siblings. The parameter list implies you need a prompt and a local reference image, but there is no statement of when image-to-image editing is appropriate versus alternatives like r-pic or i-pic. An agent must infer selection criteria entirely from the tool name and parameter shapes.

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