fillet

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

Annotations mark it as a non-readonly, non-idempotent mutation, and the description adds a genuinely non-obvious side effect: tangency propagation ('Edges tangent to the chosen ones are rounded too'), which is exactly the kind of detail annotations cannot carry. It still omits failure modes (radius too large for the edge) and whether partial success is possible.

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?

Three compact sentences, front-loaded with the operation, then per-parameter semantics, then the propagation caveat. No filler and no restatement of the tool name.

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?

With one documented parameter, two undocumented point arrays, and an output schema present, the description covers the essentials an agent needs to call it. Only the mutual-exclusivity/at-least-one requirement for the point arrays is missing, which is a small but real hole for a 3-parameter tool.

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 only 33% (radius only), so the description must compensate, and it does: it defines edge_points and face_points semantics plus units and coordinate frame ([x, y, z] in mm, model coordinates). The remaining gap is that it never states that at least one of edge_points/face_points must be supplied, leaving the required combination ambiguous.

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 ('Rounds edges') plus the defining constraint ('constant radius'), which cleanly separates it from the point-selection siblings (select_edge_at_point) and adjacent features. It does not explicitly contrast with chamfer or sketch_fillet, so an agent must infer the distinction, but the geometric intent 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?

Usage is only implied: the two alternative targeting modes (edge_points vs face_points) are described, which hints at when to use which, but the description never says when to call fillet rather than chamfer, skirt, or sketch_fillet, nor what prerequisites exist. Minimum-viable routing guidance.

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