add_fillet

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds the unit convention (mm, degrees, kg) that governs radius values. It does not, however, say what geometry is consumed or altered, whether edges are re-selected on re-run, or what the engine's error evidence looks like.

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?

Purpose is front-loaded in a short first sentence, which is good. The remaining two sentences are thin boilerplate that describe general platform conventions rather than anything specific to filleting, so they do not fully earn their place.

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?

This is a destructive six-parameter geometry mutation with no output schema and no parameter documentation. For that complexity the description is far too sparse: edge selection format, what happens on invalid radii, and the shape of returned measurements are all left to guesswork.

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% across six parameters, so the description must carry the load. It only clarifies that lengths are in mm, implicitly covering radius_mm, radii_at_mm and skip_shorter_mm. The most ambiguous parameter, edges (a string defaulting to "all"), plus tangent_propagation and name receive no explanation of accepted syntax or selection semantics.

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?

"Add fillet" is a specific verb plus resource, so an agent can tell it creates a rounded edge feature. It does not distinguish itself from adjacent siblings such as add_chamfer or add_full_round, so the reader must infer which rounding tool applies.

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?

There is no guidance on when to pick this over add_full_round or add_chamfer, no prerequisites (must a part be active? must edges exist?), and no exclusions. "Inspect verified measurements and error evidence" hints at a verification step but never says what conditions cause failure or how to recover.

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