sketch_fillet

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

With no annotations, the description carries real weight: it discloses that Fusion trims both curves (invalidating refs), that the operation is not fully atomic, the precise rollback semantics when dimensioning fails, and the warning code `fillet_dimension_failed`. That is unusually strong, though it does not cover permissions, failure modes for bad radius values, or what `status` and `profiles` in the result mean.

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 anatomy statement is front-loaded, followed by the ref-staleness consequence, the atomicity caveat, the return shape, and one example line. Every sentence carries distinct information with no filler.

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 an 8-parameter mutation tool with no output schema and no annotations, the description supplies the return shape, side effects, failure semantics, and recovery path. An agent has enough to call it correctly and handle the result.

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 75%, so the baseline is already offered by the schema, and the description reinforces the pick-point default semantics and implies the radius accepts an expression. Most of the added value is duplicative of the schema's own point1/point2/radius descriptions rather than new information.

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?

"Round ONE corner between two curves with a tangent arc of `radius`" gives a specific verb, resource, and geometric operation, and the explicit "one corner per call" scope separates it from a general fillet. An agent can distinguish it from feature_fillet and sketch_trim on the name plus this sentence alone.

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?

It states the per-call limit and the follow-up workflow: refresh curve refs from the result or sketch_get before the next fillet. It also names concrete alternatives and the condition for each — dimension the arc with sketch_dimension or remove it with sketch_delete.

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