Skip to main content
Glama
nx-ai-bridge

nx-ai-bridge

by qiuyekai

create_sketch

Create an empty sketch on a principal plane, a planar face, or a custom plane defined by origin, x-axis and normal. Returns the sketch name used to build profiles for extrusion and revolution.

Instructions

Create an empty sketch on a principal plane, on an arbitrary plane, or on a planar face. Returns the sketch name used by sketch_* tools, extrude and revolve. Sketch coordinates are 2D (x, y) in the sketch plane: for XY the sketch x/y are absolute X/Y (normal +Z); for XZ they are absolute X/Z (normal -Y); for YZ they are absolute Y/Z (normal +X). The result reports origin, x_axis, y_axis and normal. Units: millimetres (mm) and degrees.

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
faceNoPlanar face to sketch on (same selector format as FACES).
nameNoOptional sketch name (letters, digits, underscore). Auto-generated when omitted.
planeNoPrincipal plane (ignored when `face` or `x_axis`+`normal` is given).XY
normalNoCustom plane: plane normal. [x, y, z]
originNoSketch origin in absolute coordinates. [x, y, z]
x_axisNoCustom plane: direction of the sketch x axis. [x, y, z]

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does substantial work: it discloses the return payload (sketch name plus reported origin, x_axis, y_axis, normal) and the coordinate conventions per plane. It omits error behavior, persistence, and whether a duplicate name is rejected — gaps, but the core behavioral contract is present.

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

Conciseness4/5

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

Front-loaded with the action and the three placement modes, then the return contract, then the coordinate-frame details. The per-plane mapping is verbose but earns its space because it prevents axis mistakes; a slightly tighter phrasing would push this higher.

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 6-parameter geometry-creation tool with no output schema and no annotations, the description covers purpose, return shape, coordinate conventions, and units — enough to invoke it correctly. Missing are preconditions and failure modes, which keeps it below a 5.

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 100%, so the baseline is 3, but the description adds genuine meaning the schema lacks: it maps each plane enum value to absolute model axes and the resulting normal (+Z for XY, -Y for XZ, +X for YZ), and declares units as millimetres and degrees. That mapping is exactly the information an agent needs to place 2D sketch coordinates correctly.

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

Purpose5/5

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

States a specific verb and resource ("Create an empty sketch") and enumerates the three placement modes: principal plane, arbitrary plane, planar face. It also roots the tool in the wider catalog by naming sketch_*, extrude, and revolve as consumers of the returned sketch name, which separates it from those siblings.

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

Usage Guidelines4/5

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

Clear context is given: the result is the sketch name consumed by sketch_* tools, extrude, and revolve, which implies this is the prerequisite step before those operations. It does not state exclusions or failure conditions (e.g. what happens if the named face is non-planar), so it stops short of a 5.

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