upload_image

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

Adds meaningful behavioral context beyond the sparse annotations: the uploaded file lands in the input folder, exactly one of image_path or image_base64 must be supplied, and mask_for changes the behavior to upload as a MASK instead of an image. It does not cover the effect of the overwrite parameter, which could be a destructive operation, nor the filename derivation semantics; this is a minor gap given the destructiveHint annotation.

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?

Two sentences with zero filler; the core purpose is front-loaded and the second sentence captures the two critical behavior twists (exclusivity and mask mode). Every sentence earns its place and does not repeat schema contents.

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?

Given the tool's real complexity (6 params, 0% schema coverage, limited annotations), the description covers the highest-risk information: the destination, the input modes, and the mask variant. An output schema exists so the return value is already covered, but the description still omits overwrite and subfolder edge behavior, which an agent may need for correct usage.

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?

With 0% schema description coverage, the description carries the full burden and largely delivers: it explains image_path (local file) vs image_base64, their mutual exclusivity, and decomposes mask_for's shape with its subfields. It is silent on name, subfolder, and overwrite, whose semantics are inferable from their names and defaults, so the compensation is solid but not exhaustive.

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 and resource: uploads a source image into ComfyUI's input folder so LoadImage can use it, and names the use cases (img2img / inpaint / ControlNet). This clearly distinguishes it from the sibling tools, especially save_output which moves data out rather than into the ComfyUI input folder.

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?

Provides clear context for when to use this tool: before workflows that need LoadImage to reference an input image for img2img, inpaint, or ControlNet. It documents the exclusive either/or of image_path vs image_base64 and the mask_for alternative mode. It does not explicitly state when not to use it or name a sibling as an alternative, so no exclusion is given.

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