inpaint

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

With no annotations, the description carries the full burden and discloses meaningful behavior: the output lands on a NEW layer with a soft mask that can be moved, faded, or deleted like any layer, plus that generative backends call ComfyUI or an online service. It omits cost/permission/connection requirements for the online services and async behavior.

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?

Three dense sentences, front-loaded with the core action and mode-selection logic, then output behavior. Nearly every clause carries information, though the parameter notation is compact enough to be slightly terse.

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 10-parameter, no-output-schema tool, the description covers behavior and the most important inputs but leaves four parameters (seed, ellipse, feather, project) and any return/error semantics unexplained. Adequate but with clear gaps an agent would need to infer.

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 does so for box (format and px units), mask_path, points, size, prompt, and backend. However, seed, ellipse, feather, and project are left entirely undocumented in both schema and description.

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+resource ('Remove an object / fill an area') and distinguishes itself from siblings like remove_background, edit_image, and paint_stroke by naming the two operating modes (remove vs. generative fill). An agent can tell what it does without opening the 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?

Clearly routes between the two modes: 'No prompt = remove (classic fill)' vs. 'With prompt = generative fill', and names concrete backends (openai, gemini, stability). It lacks explicit comparison to sibling tools like edit_image or generate_image, so it stops short of full when/when-not guidance.

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