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

Annotations already declare readOnly, idempotent, non-destructive, no open world, so safety is covered. The description adds useful context beyond that: what the comparison returns (overlay, difference map, pixel/shape misses) and that 'candidates' draws nothing, plus that 'measure' returns a gridded crop and colour runs. Return format is implied rather than detailed.

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 purpose and reasonably short, but the first sentence is a run-on list ('overlay, difference map, pixels off and the shape misses left') that is cryptic rather than crisp. Every sentence carries information but the phrasing sacrifices clarity for density.

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 complex 7-param tool with nested objects and no output schema, the description covers the main comparison behavior and the measure/candidates modes adequately. Return-value specifics are only loosely implied (overlay, difference map named but not structured), leaving a minor gap.

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 baseline is 3, but the description adds meaning beyond schema: it explains 'candidates' score edits without drawing and that 'measure' reads the image itself rather than comparing. These clarify two of the more subtle parameters beyond what the schema text conveys.

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+resource: 'Measure your drawing against the picked image,' and enumerates the outputs (overlay, difference map, pixels off, shape misses). Clearly a comparison/measurement tool distinct from siblings like set_reference_image. Somewhat dense phrasing but the purpose is unmistakable.

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?

Gives clear usage contexts: compare a drawing to score it, use 'candidates' to score edits before sending, and use 'measure' to read the picked image before/while drawing. It does not name explicit alternatives or when-not-to-use cases, but the modes and their conditions are stated.

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