Skip to main content
Glama

Add Dimension

add_dimension

Adds annotations to FreeCAD drawing pages for overall extents, true edge lengths, hole diameters or radii, angles, and point-to-point measurements with optional tolerances.

Instructions

Add dimension(s) to a drawing page. Modes (pick one):

  • auto=True: overall horizontal + vertical extents for every part-view (or only views, by name or projection code).

  • view + edge=: true length of a model edge (the real length, not the foreshortened projection).

  • view + kind='diameter'|'radius' + edge=: ⌀/R of a hole or arc.

  • view + kind='angle' + face=: included angle (2×) of a cone/countersink/taper; half_angle=True for the half-angle.

  • view + from_point/to_point ([x,y,z] model points): point to point. view: a view handle, object name, or projection code ('Front', 'Top', ...). kind: 'aligned' (default) | 'horizontal' | 'vertical' | 'diameter' | 'radius' | 'angle'. tolerance: rendered next to the value: {"sym": 0.1} for ±0.1, {"plus": .., "minus": ..}, or {"fit": "H7"} / {"fit": "H7/g6"} (ISO 286 hole-side limits at the basic size). Returns {dimensions: [{handle, name, type, value}, ...]}; value is the true measured size.

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": {
      "page": "<page>"
    },
    "name": "add_dimension"
  }
}

Input Schema

NameRequiredDescriptionDefault
autoNo
edgeNo
faceNo
kindNoaligned
pageYes
viewNo
viewsNo
to_pointNo
toleranceNo
workspaceNoRun this call in this named workspace
from_pointNo
half_angleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.7
    • addedInput schema / properties / workspace
      Added value: +{
      +  "default": "",
      +  "description": "Run this call in this named workspace",
      +  "title": "Workspace",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare the mutation/scope profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower; the description adds genuine context by explaining that dimensions are rendered with tolerance text, that edge values are true lengths rather than foreshortened projections, and by documenting the return shape {dimensions: [{handle, name, type, value}]}. It omits failure modes (invalid edge/face tags) and whether the change is transactional/reversible.

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 mode list, then a compact glossary of shared parameters and the return value — every block earns its place. It is long, but the density is justified for 12 parameters; minor redundancy in restating kind twice.

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

Completeness5/5

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

For a 12-parameter mutation with no output schema and near-zero schema descriptions, the description covers mode selection, parameter meanings, tolerance encoding, and the return value — everything needed to issue a correct call except page/workspace plumbing, which the schema titles convey.

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

Parameters5/5

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

With only 8% schema coverage and no enums declared in the schema, the description carries nearly the whole burden: it defines auto, views, view (handle/object name/projection code), edge, face, from_point/to_point as [x,y,z], half_angle, and spells out the kind values and the tolerance dict forms ({sym}, {plus,minus}, {fit}). Only 'page' (required) and 'workspace' are left to the schema titles.

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 ('Add dimension(s) to a drawing page') and immediately enumerates the mutually exclusive operating modes (auto extents, edge true length, diameter/radius, angle, point-to-point). This clearly separates it from drawing siblings such as add_annotation, add_gdt_callout, and add_feature_note.

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?

The 'Modes (pick one)' list gives explicit conditions under which each parameter combination applies, e.g. view+edge for a true-length edge and view+kind='angle'+face for an included cone angle. It does not, however, say when to prefer this tool over add_gdt_callout/add_annotation or state prerequisites like an existing drawing page.

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