Extrude

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

Adds substantial context beyond the annotations: it explicitly warns that omitting target_body_name in cut/intersect mode cuts EVERY body the tool geometrically reaches, and states unit conventions (cm, degrees). These are exactly the behavioral facts an agent cannot derive from readOnlyHint/idempotentHint/destructiveHint. Note the tension with destructiveHint=false, but the description is not claiming a different operation type, so it is not a direct contradiction.

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 tight sentences, front-loaded with the purpose and the safety-critical warning. The target_body_name caution largely duplicates the schema's own description text, which is the only redundancy.

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 5-param, no-output-schema mutation tool, the critical gaps are covered: units, the collateral-cut risk, and the target_body_name mitigation. Missing minor items such as the meaning of profile_index or behavior when no skippable profile exists keep it from a 5.

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?

With schema coverage at only 20%, the description carries most of the load and does so for the highest-risk items: the cm/degree unit convention (a classic CAD footgun) and the consequences of an unset target_body_name. It leaves profile_index and direction semantics to the schema/defaults, so it is not fully compensatory.

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 ('Extrude a sketch profile'), which cleanly separates it from revolve, loft, and sweep, all of which need different inputs. It does not name or contrast against those siblings, so it stops short of the top score.

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?

It gives a conditional rule for a *parameter* (pass target_body_name for cut/intersect when multiple bodies exist), but nothing about when to choose extrude over revolve/loft/sweep, which is the real selection problem here. Usage is implied by 'sketch profile' rather than stated.

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