Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Pattern

part_pattern

Creates circular, linear, or mirror patterns of part features in KOMPAS-3D, with optional controlled step spacing and variable-driven counts. Returns a verification receipt and full change details.

Instructions

Circular / linear / mirror pattern of features. Circular without step = copies evenly over the full circle, and they stay even when the count changes — to drive the count by a variable n, bind only the pattern's count variable (expr 'n') via variables_set. A given step is the angle (circular) or distance (linear) between ADJACENT copies. Returns a receipt: created object handles, volume/mass before and after, backup path. The whole call is ONE Ctrl+Z for the user; if verification fails the model is restored and VERIFY_FAILED is returned.

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>",
      "kind": "<kind>",
      "features": "<features>"
    },
    "name": "part_pattern"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
axisNocircular: rotation axis; linear: direction (X|Y|Z|obj:|topo:)Z
kindYes
nameNoMeaningful feature name for the tree, e.g. 'Отв_крепёжные_6xD11'
stepNocircular: degrees (default 360/count); linear: mm
countNoinstances incl. the original
planeNomirror plane XY|ZX|ZY|obj:|topo:
featuresYesobj: handles of the features to copy

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.2

TDQS

A4.5/5.0
Behavior5/5

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

Beyond annotations it discloses the return payload (created object handles, volume/mass before and after, backup path), atomicity (the whole call is one Ctrl+Z), and failure behavior (model restored, VERIFY_FAILED). That is exactly the mutation-risk context the annotations only hint at via destructiveHint=false.

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?

It is front-loaded with purpose, then semantics, then return/rollback behavior, and nearly every clause carries information. The em-dash-heavy middle sentence packs multiple ideas together, which slightly hurts scannability but not correctness.

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 an 8-parameter mutating tool with no output schema, the description covers return values, atomicity, and failure handling well. Remaining gaps are modest — for example axis/plane semantics and whether all features must belong to the same document are left implicit.

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 88%, yet the description still adds real meaning: step measures the interval between ADJACENT copies in both modes, and count changes preserve even distribution. Axis, plane, name, and features are left entirely to the schema, so it is valuable but not exhaustive.

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?

The opening line names the specific operation (pattern of features) and enumerates the three supported modes (circular, linear, mirror), which is exactly the disambiguation needed against siblings like part_extrude or part_revolve. An agent can tell what this tool does without opening the schema.

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?

It gives concrete operating guidance: omit step for an even full-circle distribution, and to drive count from a variable n, bind the count via variables_set — an explicit routing hint to a named sibling. No when-not-to-use or exclusion is stated, which keeps it 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.