catia_list_faces

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

Annotations already declare readOnlyHint and destructiveHint, and the description adds beyond that: it discloses that indices change whenever the model changes while centroids remain stable, which affects how outputs should be used. It also scopes the operation to visible solid geometry and clarifies normals only apply to planar faces. This is meaningful behavioral context without contradicting annotations.

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?

Two sentences, front-loaded with the operation and output fields, then a focused stability note that directly informs usage. No filler or repetition of schema details.

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?

Given no output schema, the description enumerates the returned face data (index token, centroid, area, normal) and gives practical token-stability guidance. It could add return format/pagination details or clarify behavior when no visible solid geometry exists, but for a simple read-only list tool with well-covered parameters this is nearly complete.

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?

The input schema covers all parameters at 100% with adequate descriptions (limit maximum and include_metrics performance cost), so the description need not repeat them. The description does not add parameter-level semantics beyond the schema; its mention of centre of gravity/area/normal describes output content rather than parameter behavior.

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 and resource: 'List the faces of the visible solid geometry in the active document.' This distinguishes it from sibling tools like catia_list_edges and catia_list_vertices by naming the resource type, and includes output details (index token, centroid, area, normal) that make its purpose concrete.

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 context: it targets faces of visible solid geometry in the active document, and the second sentence tells when to use face@x,y,z tokens over face#n ('anything you will reference more than once'). It does not explicitly name alternatives or exclusions, so it falls short of a 5 but provides useful selection guidance.

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