Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Add dimensions

drw_add_dimension

Add associative linear, diameter, radius, angle, or roughness dimensions to a drawing view using model coordinates so dimensions bind to part geometry and follow model changes.

Instructions

Associative dimensions on a drawing view; points are MODEL coordinates (mm, model origin, e.g. from inspect_model/select), projected onto the view. Put points on real edges/vertices of the part so the dimension binds to the geometry and follows model changes (result associative). linear: p1, p2 (+ diameter_sign for ⌀ of a shaft on its side view); diameter/radius: center + radius of a circle seen as a circle in this view; angle: vertex + a point on each line (chamfers, slopes); roughness: p1 on the surface's edge + text (values from the user, ГОСТ 2.309). All dimensions of one call = one Ctrl+Z. Check with view_capture; inspect_model on the drawing lists what is there.

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": {
      "doc": "<doc>",
      "view": "<view>",
      "dimensions": "<dimensions>"
    },
    "name": "drw_add_dimension"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
viewYesnumber of an associative view (from drw_create_views)
dimensionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.3/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: model-coordinate input projected onto the view, binding/associativity only when points lie on real edges or vertices, and the undo grouping ('all dimensions of one call = one Ctrl+Z'). The annotations already cover mutability and safety, and the description never contradicts them; the main unstated behavior is what happens on non-edge points or invalid views.

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 coordinate system and binding rule, then kind-by-kind semantics, then verification advice; every sentence carries information. It is dense and parenthesis-heavy, which slows parsing for an agent scanning quickly, but there is 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 three-parameter mutation with no output schema, the definition covers coordinate frame, per-kind inputs, undo scope, the associativity outcome, and a verification path. Missing only failure behavior (points off geometry, view out of range) to be fully self-sufficient.

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 67% and the schema itself documents most fields, but the description adds real meaning: which parameter combinations apply per kind, that diameter_sign means the ⌀ symbol on a side view, that arc_radius is in sheet mm, and that roughness text comes from the user per ГОСТ 2.309. Some fields (prefix/suffix, orientation, angle default) are only partially explained.

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 associative dimensions on a drawing view) and enumerates the supported dimension kinds with the geometry each requires. It is clearly separable from siblings like drw_add_positions or view_capture, which are named only for cross-reference.

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?

Gives per-kind routing guidance (linear vs diameter/radius vs angle vs roughness) and tells the agent to verify with view_capture and to use inspect_model on the drawing. It stops short of explicit when-not or precedence rules against sibling tools such as drw_add_positions, so it is strong context rather than full exclusion logic.

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