new_canvas

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

With no annotations, the description carries the full burden. It does well to disclose that a GIMP window is opened and to return a display_opened flag, but it omits side effects an agent needs: whether the new image becomes the active/selected image, that the canvas is unsaved until save_xcf/export_image, and what happens on failure or if the server is not running.

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?

Front-loaded with a one-line purpose followed by Parameters/Returns/Examples sections, which is appropriately structured for a 6-parameter tool. Slightly redundant in that the three examples restate defaults already given in the parameter list, but the examples do add concrete call shapes.

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?

There is no output schema, so the explicit Returns block (image_id, confirmed dimensions, color_mode, display_opened) is genuinely necessary and present. The main gap is state-behavior around the newly created image and error conditions, but for a creation tool this is close to complete.

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%, and the description fully compensates: every one of the six parameters gets meaning, defaults, and accepted value formats — notably the fill parameter's CSS color name/hex/rgb() syntax and the enumerated color_mode values, none of which are encoded in the schema (0 enums).

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 — 'Create a new blank canvas in GIMP' — and adds the observable outcome 'open it in a display window.' This clearly separates it from siblings like open_image (existing files) and resize_canvas (modifying existing canvases).

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?

Usage is only implied: an agent can infer this is the entry point for starting from scratch rather than loading a file, but the description never says when to prefer this over open_image or when not to call it (e.g. if an image is already active). No prerequisites or alternatives are named.

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