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

Adds significant behavioral detail beyond sparse annotations: costing credits by output resolution, creating a NEW generation in the source's own project (side effect), and optional zoom/extend behavior. This is exactly the kind of context that helps an agent anticipate side effects and costs, and it does not contradict readOnlyHint=false or destructiveHint=false.

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 sentences, each carrying distinct information: the core operation, the cost/side-effect warning, and optional parameter usage. No fluff, and the most critical behavioral notes are front-loaded. Slightly compact but appropriately structured.

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 mutation tool with a nested object, enums, no output schema, and sparse annotations, the description covers the key aspects: side effect (new generation), cost, and optional parameter behavior. It does not mention the return value or whether the operation is async, but enough is provided for correct invocation in most cases.

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?

The schema already describes zoom, extend, and resolution with decent detail (60% coverage). The description adds a little emphasis on 'zoom < 1' and 'restrict directions with extend' but does not clarify generation_id or target_aspect_ratio beyond the schema. With 60% coverage, the baseline 3 is appropriate.

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?

The description clearly states a specific verb ('outpaints') and resource ('existing generation') with a defined outcome (bigger canvas / new aspect ratio). It distinguishes the tool from siblings like upscale_image (which increases resolution) and generate_image (which creates from scratch) by focusing on extending the scene beyond original edges.

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 context is implied: use this when you need to expand an existing generation to a larger canvas or new aspect ratio. It mentions optional controls for restricting directions and zooming out, but does not explicitly name alternatives or state when not to use it, leaving some routing to inference.

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