sketch_offset

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

With no annotations, the description carries the full burden and does meaningful work: "All or nothing" discloses atomicity on failure, and the parametric vs. plain-copy branch depending on the Fusion version is a non-obvious behavioral trait that would otherwise surprise an agent (it creates an extra `dimension` entity in one mode). It also inlines the return shape. Missing: what happens on self-intersecting offsets and whether source curves are preserved.

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 core operation and its main semantic switch (`chain`) are front-loaded in the first sentence, followed by the parametric caveat, the return shape, and a single example. No sentence is padding — each adds either semantics, a behavioral branch, or a concrete call shape.

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?

Covers the essentials for a six-parameter mutation: what it does, the chain scope, the parametric branch, and the response fields, which compensates for the absent output schema. It stops short of error behavior (degenerate offsets, invalid curve refs) — the main remaining gap for a creation tool with no annotations.

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 already 83%, so the baseline is 3; the description adds meaning by explaining what `chain` actually does (extends to the connected loop) and by showing that `distance` accepts a named expression ("wall") that is carried into a dimension. The example clarifies the `side_point` side-selection semantics with concrete values, which the schema only gestures at.

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 — offset sketch curves by a distance toward a side point — plus the scoping modifier that `chain=true` extends to the whole connected loop. The mention of "curves" and the required `sketch` ref distinguishes it from the body/surface offset siblings (surface_offset, feature_offset_faces) without needing to name them.

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?

Provides a concrete usage scenario ("inner wall of a closed outline") with a worked call, which tells the agent the intended shape of the invocation. It does not explicitly exclude cases (e.g. when to prefer sketch_transform or feature_offset_faces over this), so the routing guidance is implicit rather than exhaustive.

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