Make Sketch

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

Annotations already indicate mutation, no destructive effect, and no open-world changes. The description adds the plane options and the return value {handle, name}, which is helpful given no output schema. It doesn't cover side effects or prerequisites, but annotations cover the safety profile.

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?

Two sentences with no filler. The plane options and return value are efficiently packed. It could be expanded, but it does not waste words.

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 3-parameter tool with no output schema and 0% schema coverage, the description is too thin. It omits body and name semantics, and doesn't connect to follow-on sketch tools or prerequisites. It tells the agent what it returns but not the full invocation contract.

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 0%, so the description must document parameters. It explains 'plane' with allowed values and datum-plane handle, but 'body' and 'name' are left undocumented. Body is required and likely a handle, yet no hint is given; name's role is absent.

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 (create), resource (sketch), and context (in a Body, attached to a plane). It distinguishes from close_sketch and geometry-add tools by indicating this creates the sketch container itself, though it does not explicitly name sibling tools.

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 implies this is the entry point for sketching (create before adding geometry) but gives no explicit when-to-use or alternative routing. It doesn't mention that add_sketch_geometry/add_sketch_constraint are needed after, nor when to use a datum plane vs origin plane.

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