feature_extrude

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

With no annotations, the description carries the full burden and does: it discloses failure modes and side effects (INVALID_PARAMS changes nothing, ENTITY_NOT_FOUND returns current profiles, FUSION_API_ERROR rolls the timeline back, a warning keeps the feature and reports in `health`), plus the critical ref-staleness caveat after later features. This is exactly the behavioral context an agent cannot infer from the schema.

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 then sectioned into Units, Refs, Modes, Surface, Errors, Returns, Examples, which is easy to scan. It is long and the Examples section largely restates what the Modes bullets already say, so a little trimming is possible, but nearly every sentence earns its place given 14 parameters.

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 14-parameter, high-complexity feature tool with no output schema, the description documents the full return object (feature ref, health state/message, created/modified/removed bodies, optional component) and even tells the agent body geometry must be fetched via inspect_*. Nothing an agent needs to invoke or interpret results is missing.

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 cross-parameter semantics the schema does not encode: negative distance reverses direction, symmetric requires side1 be a distance, side2 applies only to two_sides, symmetric_full_length picks total vs half, and a string value becomes a driven Fusion expression. The units/string-vs-number convention is also restated usefully.

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?

Opens with a specific verb plus resource ('Extrude sketch profiles, planar faces or sketch texts into a solid') and immediately scopes the operation variants (cut/join/intersect) that distinguish it from feature_revolve/sweep/loft siblings. An agent can tell exactly what this tool produces without opening the schema.

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?

Explicitly maps the three modes to their required fields and gives condition-dependent advice ('operation="cut" with through_all and direction="negative" cuts down through a body below the sketch', 'is_solid=false ... no thin'). It explains where refs come from and how to get them, but never names an alternative sibling tool (e.g. feature_revolve) as the choice when profiles are non-planar, so it stops short of full when-not guidance.

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