create_sketch_arc

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

No annotations are provided, so the description carries the behavioral transparency burden. It does disclose one important behavioral rule: `faceId` takes precedence over `plane`, which helps the agent avoid a common mistake. However, it does not describe side effects, whether this creates a standalone sketch or adds an arc to an existing sketch, default behavior when neither surface is provided, or what the agent should expect in the response. The precedence detail is valuable, but overall behavioral coverage is thin.

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 description is three short sentences with no filler. The purpose is front-loaded in the first sentence, and the second and third sentences compactly convey the surface-selection guidance and precedence rule. Every sentence earns its 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?

The 100% schema coverage compensates for most parameter-level gaps, making the description workable as a minimal definition. However, for a 14-parameter CAD mutation tool with no annotations and no output schema, the description leaves ambiguity about the sketch lifecycle: does it create a brand new sketch containing an arc, or does it add an arc to an existing sketch? It also gives no indication of return values or follow-up actions. This is adequate but not complete.

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?

The schema description coverage is 100%, and the input schema already documents every parameter with units, defaults, enum values, and constraints. The description adds only the relationship between `plane` and `faceId`, which is useful but largely redundant with the schema's `faceId` property description. Per the baseline for high schema coverage, the description does not need to repeat parameter details, and it does not do so.

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?

The description opens with a direct verb+object, 'Create an arc sketch', which states exactly what the tool produces and distinguishes it from sibling sketch tools like create_sketch_circle, create_sketch_line, and create_sketch_rectangle. The resource type is specific and recognizable, so an agent can identify the tool's role without inspecting the schema.

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?

The description gives concrete guidance for the main surface-selection ambiguity by telling the agent to pass either `plane` or `faceId`, and explicitly states the precedence rule (`faceId` wins when both are given). It also tells the agent where to obtain `faceId` (from `list_entities`). It does not explicitly compare this tool to alternative sketch-creation siblings or list prerequisites, but the context it provides is clear and actionable.

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