feature_web

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

With no annotations, the description carries the full burden and does so thoroughly: no operation parameter, the join target is implicit, defaults resolve to the single touched solid body, and each failure mode is enumerated with its consequence (INVALID_PARAMS with nothing changed, INVALID_PARAMS with details.candidates, FUSION_API_ERROR plus timeline rollback). The side2 API limitation and version fallback are disclosed, which the agent could not otherwise know.

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 the one-line definition, then logically grouped Units / Refs / Errors / Returns / Example blocks. Dense but every block is functional; the errors paragraph is long yet each clause is a distinct failure mode an agent must handle.

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 7-parameter geometry mutation with no annotations and no output schema, the description supplies the missing pieces: return shape is stated inline, error taxonomy maps to remediation, default target resolution is explained, and the recovery path (execute_python) is named. Nothing material is left for the agent to guess.

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 baseline is 3, and the description adds real semantics beyond it: thickness and depth.distance are interpreted in `units`, a string value is a Fusion expression, and curves must be open sketch entities from sketch_draw in one sketch. The worked example ties the parameters together with a concrete depth object.

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 concrete verb plus resource and a precise physical definition ('a network of thin walls from several open sketch curves ... joined to the body it meets'), including a parenthetical use case. It implicitly separates itself from a single-curve rib via 'network of thin walls' and the 'rib/web' phrasing in params, but never names the sibling feature_rib, so the differentiator must be inferred.

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?

Establishes clear prerequisites (curves must come from sketch_draw, all in one sketch inside the body) and an explicit exclusion (circles and closed splines are refused). It also routes the agent to execute_python when the Fusion API version lacks web features. What is missing is an explicit 'use feature_rib instead when you have a single curve' statement.

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