Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Mate components

asm_mate

Creates assembly mate constraints between component references for coincident, concentric, parallel, perpendicular, tangent, distance, angle, or symmetric, with one-step undo and failed-check restore.

Instructions

Mate constraint between two references of components: faces/edges from select(created_by=) or obj: planes/axes. kinds: coincident (faces touch), concentric (axes of cylinders), parallel, perpendicular, tangent, distance (mm), angle (deg). The answer lists component boxes after the mate. Returns a receipt; one Ctrl+Z for the user; on a failed check the assembly is restored (VERIFY_FAILED).

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>",
      "obj1": "<obj1>",
      "obj2": "<obj2>"
    },
    "name": "asm_mate"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesAssembly document handle
kindYes
obj1Yestopo:/obj: reference on the component that should MOVE
obj2Yestopo:/obj: reference it is mated to
planeNosymmetric: plane of symmetry (XY|ZX|ZY | obj: plane | topo: face) — obj1 and obj2 end up mirrored about it, e.g. a part centred between its two side faces; prefer it to a distance that only happens to centre
valueNomm for distance, degrees for angle
alignmentNoorientation of the mated faces; omit to let KOMPAS choose (recommended)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that the call returns a receipt, that the user needs one Ctrl+Z to undo, and that a failed check restores the assembly under VERIFY_FAILED. That reversibility and verification contract is exactly the behavioral context a mutation tool needs and is not derivable from readOnlyHint/destructiveHint/idempotentHint. It is consistent with destructiveHint=false since the operation is undone in one step and rolled back on failure.

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?

A single dense paragraph that front-loads the operation, then the kind vocabulary, then the return/undo/failure behavior. Nearly every clause carries information. It is packed but not padded; the only minor cost is that the kind definitions and behavioral notes run together rather than being separated.

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 7-parameter mutation tool with no output schema, it covers the essentials: what the call does, valid inputs, what comes back (a receipt plus component boxes), and what happens on failure. The remaining gap is the receipt's contents and whether the mate is added to the feature tree or persists after the call, which an agent might want to know.

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 86%, so the baseline is 3, but the description genuinely adds meaning the enum does not: it defines what each kind geometrically means (coincident, concentric on cylinder axes, tangent) and restates units. The obj1/obj2 sourcing rule (select(created_by=...) or obj: planes/axes) also enriches arguments the schema only labels as 'topo:/obj: reference'. Only the plane/value/alignment semantics remain solely in the schema.

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?

Opens with a specific verb+resource: 'Mate constraint between two references of components', which is unmistakably distinct from siblings like asm_add_component or asm_edit. It then names the supported constraint kinds, so an agent knows the exact operation. It stops short of explicitly contrasting itself with any sibling, which keeps it at 4 rather than 5.

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 a concrete prerequisite for the reference arguments ('faces/edges from select(created_by=<component obj>) or obj: planes/axes'), which tells the agent when the call is valid and how to source inputs. The inline parentheticals for each kind (coincident = faces touch, concentric = axes of cylinders) guide kind selection. It does not state when to prefer a different tool or when to avoid mating, so no exclusion guidance.

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