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

Strong disclosure beyond the annotations: the exact cost (0.03 USDC on Base), the explicit statement that this tool does not analyze, sign, or charge, and an enumeration of what is returned (endpoint, echoed input, payment instructions). This is exactly the kind of side-effect clarification readOnlyHint/openWorldHint cannot convey. It stops short of describing failure modes or what the caller must do with the returned endpoint.

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?

Purpose is front-loaded in the first sentence, with cost and non-execution caveats following in a logical order. Sentences are short and mostly earn their place, though the 'does not perform analysis, sign or charge' clause overlaps with the 'Returns the canonical endpoint' sentence.

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 three-parameter, no-output-schema prep tool, the description covers the payment model, the non-execution guarantee, and the return payload well. It is incomplete on the input contract — the shape/hole geometry and threshold semantics — which is the main thing an agent needs to call it correctly.

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% for three required parameters, and the description only gestures at them with 'Checks object and hole dimensions' and 'no SVG or curve import.' It never explains the shapes array structure, point format, units, or how minWidthMm/minHeightMm are compared against geometry, so it fails to compensate for the schema gap.

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 states a specific verb and object ('Find tiny polygon objects and holes') and scopes it to pre-production checks, plus it draws a boundary ('no SVG or curve import') that helps separate it from prepare_curve_clearance and prepare_vector_health. It does not name those siblings explicitly, so classification still requires a small inference.

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?

'before production' gives a timing cue, and the exclusion of SVG/curve input implies which sibling to pick instead. However, no alternative tool is named and no prerequisite or when-not condition is spelled out beyond that one negative clause.

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