rhino_fillet_surface

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

Annotations already carry the mutation signal (readOnlyHint=false), and the 'Create' verb is consistent with that, so there is no contradiction. The description adds no behavioral detail beyond the operation: it does not disclose whether the source surfaces are kept, trimmed, or destroyed, nor does it mention failure conditions for infeasible radii or incompatible geometry. With annotations covering the safety profile, the description's thinness is tolerable but unhelpful.

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?

A single eight-word sentence that is front-loaded with the verb and wastes no words. It is efficient, though it borders on under-specification — a short clause clarifying the fate of the source surfaces would add value without bloating the definition.

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 surface-modeling operation with six nested parameters and many closely related siblings, this is too thin. It omits prerequisites (that the ids refer to existing surface objects, that the surfaces must be filletable), the fate of the source surfaces, and failure conditions. The presence of an output schema excuses the absence of return-value explanation, but the operational context remains incomplete.

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 0%, so the description must compensate, and it partially does: 'two surfaces' maps to surface_a_id and surface_b_id, and 'constant-radius' maps to radius. It adds nothing about the optional name, layer, or doc_id parameters, nor about radius units or feasibility constraints. The three required parameters are covered conceptually, but mostly because the schema titles are already self-explanatory.

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 states a specific verb ('Create') and a specific resource ('constant-radius fillet between two surfaces'). The 'constant-radius' qualifier implicitly distinguishes it from rhino_variable_fillet, and 'between two surfaces' separates it from edge-based tools like rhino_fillet_edges. However, differentiation is implicit only — it never acknowledges the near-duplicate rhino_cmd_fillet_surface in the sibling list.

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?

No guidance is given on when to use this tool versus alternatives such as rhino_cmd_fillet_surface, rhino_variable_fillet, rhino_fillet_edges, or rhino_blend_surface. The word 'constant-radius' is the only hint about scope, and there are no exclusions or routing conditions. Given the large sibling list with several overlapping surface tools, explicit usage guidance is absent.

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