sw_create_3d_sketch

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this is an additive write. The description adds the model-mm unit convention and the bend_radius purpose for tube-ready polylines, but says nothing about whether an active document is required, what happens on invalid geometry, or whether it errors when a sketch already exists.

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?

A single dense sentence covering geometry types, units, and downstream uses with no filler. It is slightly run-on, but the purpose and the entity list are front-loaded, so an agent can act on it quickly.

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 creation tool with no output schema, the description supplies the geometry vocabulary, unit convention, and integration targets, which is enough to call it correctly. The remaining ambiguity about document targeting is resolved by the doc parameter's own schema description.

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 67%, so the schema carries most parameter meaning (per-field '[x, y, z] in model mm', bend_radius min-exclusive constraint). The description reinforces entity kinds and the bend_radius semantic for tubes, but does not cover doc or name, so it neither needs to compensate heavily nor adds much beyond the schema.

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+resource (create a 3D sketch) and enumerates the supported entity types (lines, polylines with bend_radius, splines, 3-point arcs) plus the unit convention (model mm). It also implicitly separates itself from sw_create_sketch by pairing with 3D consumers such as sw_sweep and sw_structural_member.

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?

Concrete downstream use cases are given ('sweep paths for tubes, cable routes, frame layouts for sw_structural_member'), which tells the agent where this tool fits in a workflow. It stops short of naming the 2D alternative (sw_create_sketch) or stating when not to use it, so no exclusion guidance.

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