outpaint

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

With no annotations, the description carries the full behavioral burden. It does well on mechanism: it discloses that the canvas grows by pixel amounts, that a border is selected reaching `overlap` px into the old image for blending, and that the border is inpainted. It is silent on side effects that matter for a mutation tool — whether it edits the current document/layer in place, whether the result is a new layer or overwrites, and any backend/cost implications of generating multiple results.

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?

One tightly packed sentence with the core action front-loaded before the parenthetical mechanism detail; no filler. It is dense but readable, though the colon-and-clause construction slightly compresses what could be two clean sentences.

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 13-parameter generative mutation tool with no annotations and no output schema, the description covers the geometry but not the invocation surface or the return shape. An agent still cannot tell what `size`, `count`, `model`, `backend`, or `workflow` do, nor what happens to the document after the call.

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% across 13 parameters, so the description must compensate and largely does not. It explains only the four directional pixel amounts and `overlap`; the required `prompt`, plus `negative_prompt`, `seed`, `size`, `count`, `model`, `backend`, and `workflow` get no meaning, no units, no valid ranges, and no defaults restated.

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 ('extend the picture beyond its edges', 'grows the canvas') and describes the mechanism (border selection plus inpainting), which cleanly separates it from siblings like resize_canvas, scale_image, and crop_image that also change canvas geometry but add no generated content.

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 implied by the mechanism — you call this when you want new generated content past the existing edges rather than stretching or cropping. But there is no explicit when-to-use/when-not, no mention of alternatives such as generate_image or resize_canvas, and no stated prerequisites (e.g., an open document or active layer).

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