sketch_trim

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

With no annotations, the description carries the full burden and does so: it discloses that trimming replaces the curve, that Fusion cannot undo it inside a batch, that refs go stale, and that a >5 mm offset fails with INVALID_PARAMS. It also spells out the return payload (created/deleted/status/profiles), which is a meaningful addition given there is no output schema.

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?

Five short chunks, front-loaded with the action and semantics, then the per-call constraint, then error behavior, then the return shape, then a one-line example. Nothing is redundant; the example is cheap and directly useful.

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 mutating, non-undoable sketch operation with no annotations and no output schema, the description covers what is destroyed (the original curve), how refs behave across calls, the error mode, and the return fields — everything needed to call it correctly and to chain a batch of trims.

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 100%, so the schema already explains sketch, curve, point (all accepted forms) and return_profiles, including the ≤5 mm tolerance. The description reinforces the 5 mm rule and the single-curve constraint but adds no new syntactic or format detail beyond the schema — baseline 3.

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 (trim) and resource (sketch curve segment), and clarifies the exact semantics: the cut is made at the segment nearest `point` and goes back to the neighbouring intersections. That distinguishes it well from a plain delete, but it never contrasts itself with near-siblings like sketch_delete, sketch_extend, or surface_trim, which share the operation space.

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?

Gives concrete operating guidance: ONE curve per call, and after a trim the old ref is stale so the refs in the result must be used for the next trim. It also states the failure condition (point farther than 5 mm). It does not, however, say when to prefer this over sketch_delete or sketch_extend, so the alternative selection is left implicit.

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