Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

create_sketch_on_face

Starts a sketch on the flat face containing a given interior 3D point, independent of view, and returns sketch origin, axes, and point coordinates for placing geometry.

Instructions

Start a sketch on the flat body face that contains a given 3D model point (found by geometry, so the current view does not matter). The point must lie inside the face, not on an edge. The result gives the sketch origin and axis directions in model space and the point in sketch coordinates, which you need to place geometry.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "x": "<x>",
      "y": "<y>",
      "z": "<z>"
    },
    "name": "create_sketch_on_face"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesX of a point inside the face
yYesY of a point inside the face
zYesZ of a point inside the face
unitNomm, cm, m, inch or ft

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the return payload (sketch origin, axis directions in model space, point in sketch coordinates) and one failure condition (edge points are invalid). It does not say what an invalid point produces (error vs. silent snap), whether the sketch is opened for editing, or what side effect appears in the feature tree.

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?

Three sentences, front-loaded with the core action, then the constraint, then the return contract. Every sentence carries information an agent needs; nothing is repeated from the schema or padded.

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 4-parameter tool with no output schema and no annotations, the definition covers action, precondition, and return values well enough to call it correctly. The remaining gap is failure behavior for edge or off-face points, which matters for a geometry tool that can plausibly error.

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

Parameters3/5

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

Schema coverage is 100% and each coordinate is already documented as 'point inside the face', so the schema does the heavy lifting. The description adds the meaningful constraint that the point is resolved by geometry rather than by screen position, but it says nothing about the optional unit parameter.

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?

The description states a concrete verb and resource ('start a sketch on the flat body face') plus the distinctive selection mechanism: the face is identified by a 3D model point rather than by the current view. That mechanism distinguishes it from a plain plane-based sketch tool, though no sibling is named explicitly.

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?

It gives a real precondition — the point must lie inside the face, not on an edge — which implicitly tells the agent when this tool applies. It never states when to prefer it over a plane-based sketch tool or what to do if the point lands on an edge, so the routing guidance is implied rather than explicit.

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