catia_fillet

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

Annotations cover the safety profile (non-readOnly, non-destructive, non-idempotent), and the description adds meaningful behavior beyond them: tangent edges are propagated automatically, edges are searched in the active body, and multiple edges collapse into a single feature. It does not describe failure behavior when a point misses an edge.

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 core operation and scope, then the edge-identification rule and the sibling pointer. The parenthetical dialog analogy is slightly verbose but genuinely aids recognition; no wasted sentences.

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 mutation tool with no output schema, it covers the essentials: what is created, how edges are targeted, tangent propagation, and the search body. Missing only failure/validation behavior and whether the resulting feature name is returned, which the name parameter partly implies.

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 practical meaning: edges are specified by a 3D point lying on each edge (midpoint hint), and the active body is the search scope. That is more than the schema alone conveys about how to supply edge_points.

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 ('constant-radius edge fillet on one or more edges') and clarifies the key semantic that multiple edges yield ONE fillet feature, paralleling the Congé d'arête dialog. This clearly distinguishes it from siblings like catia_chamfer or catia_shell.

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 routes the agent to catia_list_edges when edge endpoints are unknown, which is exactly the prerequisite an agent needs. It lacks an explicit when-not (e.g. variable-radius or face fillets, or chamfer-vs-fillet choice), so it falls short of a 5.

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