Skip to main content
Glama
inventor-mcp-server

inventor-mcp-server

constrain

Position two components relative to each other using origin geometry, faces, or circular edges, and report any other components that move.

Instructions

Constrain two components, at any depth — by origin geometry, faces or circular edges. Prefer origin geometry: it survives part edits; face and edge numbers change with the topology.

References: "Part:1#XY" / "#XZ" / "#YZ" / "#X" / "#Y" / "#Z" / "#ORIGIN" (origin geometry), "Sub:1/Part:1#F12" (face, from find_faces), "Sub:1/Bolt:1#E4" (edge, from find_edges). A list index works as the component: "2#XY".

Says which OTHER components the constraint moved — one can drag parts you didn't mean to touch.

Args: a, b: References; a is the one meant to move. kind: "mate" (faces against each other, axes in line), "flush" (faces the same way), "angle", or "insert" (two circular edges: a bolt into a hole). offset: mm for mate / flush / insert. Its sign is easy to get wrong — give a_at too. angle: Degrees for kind="angle". a_at: Where a's face must end up, e.g. {"Z": 182.5}. If it lands elsewhere, the offset is tried with the other sign. axes_opposed: For insert: True = the components face each other (normal bolt / hole case).

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": {
      "a": "<a>",
      "b": "<b>"
    },
    "name": "constrain"
  }
}

Input Schema

NameRequiredDescriptionDefault
aYes
bYes
a_atNo
kindNomate
angleNo
offsetNo
instanceNoWhich connected Inventor to use (list_instances). Leave empty when only one is connected.
axes_opposedNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.0.0
    • addedInput schema / properties / a
      Added value: +{
      +  "title": "A",
      +  "type": "string"
      +}
    • addedInput schema / properties / a_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "A At"
      +}
    • addedInput schema / properties / axes_opposed
      Added value: +{
      +  "default": true,
      +  "title": "Axes Opposed",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / b
      Added value: +{
      +  "title": "B",
      +  "type": "string"
      +}
    • removedInput schema / properties / geometry1
      Removed value: -{
      -  "title": "Geometry1",
      -  "type": "string"
      -}
    • removedInput schema / properties / geometry2
      Removed value: -{
      -  "title": "Geometry2",
      -  "type": "string"
      -}
    • removedInput schema / properties / occurrence1
      Removed value: -{
      -  "title": "Occurrence1",
      -  "type": "integer"
      -}
    • removedInput schema / properties / occurrence2
      Removed value: -{
      -  "title": "Occurrence2",
      -  "type": "integer"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "occurrence1",
      -  "geometry1",
      -  "occurrence2",
      -  "geometry2"
      -]New value: +[
      +  "a",
      +  "b"
      +]
  2. First observedv0.8.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it warns that a constraint 'can drag parts you didn't mean to touch' and that the tool reports which components moved, and it discloses the offset-sign retry behavior ('tried with the other sign'). It doesn't say whether constraints are persistent/undoable or what a failure looks like, so not a 5.

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?

The key insight (prefer origin geometry) is front-loaded and every section — References, Says, Args — adds information. It's dense and useful rather than padded, though the reference-format line is a wall of syntax that could be organized more scannably.

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 an 8-parameter mutation tool with no annotations, the description covers reference syntax, kind semantics, both dimensional parameters, the a_at landing check, and the axes_opposed insert case. An output schema exists, so the return-reporting note is a bonus rather than a gap.

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 only 13%, so the description must compensate — and it largely does, explaining a vs b's roles, all four `kind` values, units for `offset` and `angle`, and giving a concrete `a_at` example ({"Z": 182.5}). The only undocumented parameter is `instance`, which the schema itself covers via its own description, so the gap is minor but prevents a 5.

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?

States a specific verb and resource — 'Constrain two components' — plus the supported reference types (origin geometry, faces, circular edges) and depth-independence. It's clear what it does, but it never distinguishes itself from the sibling `manage_constraints`, leaving the agent to guess whether that tool lists/edits/deletes constraints while this one creates them.

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 real selection guidance: 'Prefer origin geometry: it survives part edits; face and edge numbers change with the topology,' which is exactly the kind of tradeoff an agent needs. It also implies the workflow by naming `find_faces` and `find_edges` as the source of face/edge references. Falls short of 5 because it doesn't say when *not* to use this tool or how it differs from `manage_constraints`.

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