catia_fillet

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

Annotations only provide basic flags, so the description carries real behavioral weight. It adds valuable non-obvious behavior: edge tokens like 'edge#4' and 'edge@20,0,10', the latter surviving model changes, and the default propagation across tangent-continuous edges. It could go further by noting failure behavior when an edge token is invalid, but it materially exceeds the annotated baseline.

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 tightly packed sentences front-load the core action and then explain the two most important behavioral nuances. Every clause earns its place: reference token syntax, model-change robustness, and tangent-chain default. There is no filler or 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 CAD feature tool, the description plus 100% schema coverage gives an agent what it needs to select edges, set radius, and understand tangency propagation. It does not mention prerequisites such as active workbench/body or what the tool returns, but these are less essential for a straightforward fillet operation, making it 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?

Schema coverage is 100%, satisfying the baseline, and the description goes beyond it by explaining the edge token formats and the difference between index-based and point-based references. This is genuinely useful semantic context that the schema examples alone do not convey. Radius and propagation semantics are already well covered by the schema, so the description does not need to repeat them.

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?

The description opens with a specific verb and resource: 'Round one or more edges with a constant radius.' The qualifier 'constant radius' clearly separates it from sibling tools like catia_variable_fillet, and 'edges' separates it from face-based fillets. It also previews key behavior (tangent chains), so the tool's purpose is unmistakable.

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?

The description makes clear this is the tool for constant-radius edge rounding and explains that a single token usually rounds a whole tangent-continuous chain. It does not explicitly name alternative tools or state when not to use it, but the 'constant radius' and 'edges' framing gives enough context to select it correctly among siblings.

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