PartDesign Fillet

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

The description discloses concrete validation steps (Shape.isValid(), solid count, bounding box growth), failure behavior (feature removed, Tip restored, BlendCheckFailed raised), optional modes (per_edge, allow_partial), and a concrete motivating example. This goes far beyond the sparse annotations, which only mark readOnly/openWorld/destructive hints. No contradiction with 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?

The description is dense but each sentence adds material value: purpose, parameter semantics, validation rationale, option behavior, return structure, and error handling. It is front-loaded with the core purpose and avoids filler. The anecdote about the 40x40x1 pad justifies the validation but is not redundant. Well organized into logical chunks.

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 the tool's complexity, the description is remarkably complete. It covers input semantics, options, validation criteria, exact return fields, and failure handling. There is no output schema, so the thorough return-type explanation is essential and provided. An agent can call this tool correctly with no further documentation.

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?

With 0% schema description coverage, the description fully compensates: it specifies that edges accepts e_* tags or 'EdgeN' strings, radius is in mm and must be > 0, and explains the behavioral meaning of per_edge and allow_partial. Feature and name are covered contextually ('feature in a Body' and default provided in schema). This is excellent parameter documentation.

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 'PartDesign Fillet on edges of a feature in a Body', naming the exact verb, resource, and scope. It explicitly references fillet_edges as a sibling and clarifies the PartDesign-specific context, so an agent can distinguish this from the Part workbench tool even without opening schemas.

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 clearly implies it is for PartDesign Bodies, and the mention of fillet_edges and 'PartDesign needs it as badly as the Part workbench' signals when to prefer this over the sibling. However, it does not explicitly state exclusions (e.g., when NOT to use it or when fillet_edges would be the correct choice), so it stops short of full routing guidance.

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