drawing_extract_geometry

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

Annotations already declare this is a read-only, non-open-world operation, so the safety profile is covered. The description goes well beyond that, disclosing that dimensions are vector strokes rather than text, that a first call without origin returns paper positions, and the specific pitfalls (R vs D confusion, rounded drawn tangents differing from written values, wrong title block scale). However it is less explicit about output shape and cardinality beyond 'each entity lists its paper position', which tempers the score.

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?

Dense but front-loaded: the purpose is in the first clause, followed by the confirm-the-dimension rule, the numbered workflow, then a short 'Beware' list of failure modes. Every sentence carries information, though the paragraph is longer than strictly necessary for an experienced caller.

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?

With no output schema, the description carries the return-value burden and does so: it names the entity types returned and notes that entities carry paper positions, plus the geometry attributes (centre, R, D) in part mm. Combined with the pitfalls and workflow, an agent has what it needs to call and interpret results 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 100%, so the baseline is 3, but the description adds real operational meaning: origin is described as the paper point typically found in a first no-origin call, and scale is tied to the two-call workflow (paper coords vs part coords). It explains the intent of the origin/scale pairing rather than restating the schema.

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 ('Extract EXACT geometry from a vector PDF drawing') and enumerates what is extracted (numbered circles, arcs, line segments with centre, radius R, diameter D in part mm). It also distinguishes itself from drawing_render, which it positions as the eyeball-reading sibling rather than the measurement source.

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 an explicit three-step workflow: render the page first, call this without origin to find the axis, then call again with origin and scale. It states the selection condition against the alternative (read dimensions by eye on drawing_render, then confirm here) and explicitly says the measured value wins on disagreement.

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