Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

create_sketch

Start a sketch on a SOLIDWORKS model plane—Front, Top, Right, or a named plane—to begin 2D geometry; it is refused while another sketch is open.

Instructions

Start a sketch on one of the model's planes: Front, Top, Right (the standard planes, in any language), or another plane by name (for example 'Plane1' made by create_offset_plane). Refused while another sketch is open.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_sketch"
  }
}

Input Schema

NameRequiredDescriptionDefault
planeNoFront, Top, Right, or the exact name of a plane in the feature treeFront

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries full behavioral burden; it usefully discloses one real constraint (refusal while another sketch is open) and the plane-existence prerequisite. It omits what the call produces (sketch name/state), whether the new sketch becomes active for entity creation, and any document-state requirements, leaving meaningful gaps for a mutation tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and valid values, followed by the constraint. No redundant restatement of the tool name and no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-optional-parameter tool with no output schema, the description covers valid inputs, defaults, plane provenance, and the main blocking condition. What remains missing is the post-call state (active sketch, return value), which is modest but not trivial for an agent chaining into add_sketch_entity calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100% for the single optional plane parameter, and the description still adds value: localized plane names ('in any language'), a concrete naming example ('Plane1'), and the dependency on create_offset_plane. This goes beyond the schema's terse 'exact name of a plane in the feature tree'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (start) and resource (a sketch) constrained to the model's planes, and names concrete plane values. It builds in the notion that non-standard planes come from create_offset_plane, but never explicitly contrasts itself with the sibling create_sketch_on_face, which is the obvious alternative for an agent choosing where to sketch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context (default is Front, custom planes must exist first via create_offset_plane) and a hard precondition ('Refused while another sketch is open'), which implicitly points at close_sketch. However, there is no explicit when-to-use-this-vs-create_sketch_on_face guidance, so the agent must infer the plane-vs-face split from the wording alone.

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

Deploy Server

Other Tools