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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true): 5 credits per run with refund on failure, API key requirement, input constraints of 10 MB / 2048 px on the longest side, 7-day result link lifetime, and the critical caveat that the model redraws the whole frame so fine details of the original may change. That last point is exactly the kind of non-obvious side effect an agent needs.

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?

Five tight sentences, front-loaded with the core capability, then cost, requirements, input limits, output, and the risk caveat. No filler or restatement of the tool name.

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?

Covers cost, auth, input constraints, output lifetime and the redraw caveat, which is comprehensive for a one-shot generation tool with no output schema. The remaining gap is the execution model: the presence of a get_ai_task sibling suggests tasks may be asynchronous, yet the description simply says it 'returns a link', leaving the agent unsure whether to poll.

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 coverage is 100%, so the enum of ratios and the image_url/image_base64 descriptions already carry most semantics; the description adds constraints not present in the schema (formats PNG/JPEG/WebP, 10 MB ceiling, 2048 px limit). It does not clarify the mutual exclusivity of image_url vs image_base64 beyond what the schema implies.

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 an image to a wider or taller shape with AI') plus a concrete use case (portrait to 16:9 thumbnail without cropping the subject). This distinguishes it clearly from siblings like ai_upscale_image and ai_remove_background, which change resolution or remove elements rather than changing aspect ratio.

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?

The example use case gives a clear context for when to reach for this tool, and the file-format/size limits implicitly rule out some inputs. However, it never explicitly routes the agent away from alternatives (e.g. 'to increase resolution instead, use ai_upscale_image') and does not say whether this is a blocking call or one that requires polling via get_ai_task.

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