Skip to main content
Glama
inventor-mcp-server

inventor-mcp-server

check_interference

Read-only

Detect overlapping occurrences in an active Inventor assembly by comparing two sets, reporting full paths, volumes, and bounding boxes; optionally set aside small fastener overlaps.

Instructions

Check overlap between occurrences of the active assembly: full paths of both, volume and bounding box of each. Touching faces are not reported. Intended overlaps (gasket compression, thread in thread) show up too — read the volume and bbox.

Args: set_a: Comma-separated names, paths or patterns: "DOOR:1", "Sub:1/Part:2", "BRACKET". set_b: The same, to test against; empty = everything else. ignore_fasteners: Set aside overlaps with small Content Center members (bolts, nuts, washers, under 150 mm) — threads overlap by design. They are counted.

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": {
      "set_a": "<set_a>"
    },
    "name": "check_interference"
  }
}

Input Schema

NameRequiredDescriptionDefault
set_aYes
set_bNo
instanceNoWhich connected Inventor to use (list_instances). Leave empty when only one is connected.
ignore_fastenersNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.0
    • addedInput schema / properties / ignore_fasteners
      Added value: +{
      +  "default": false,
      +  "title": "Ignore Fasteners",
      +  "type": "boolean"
      +}
  2. First observedv0.8.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only give readOnlyHint and openWorldHint, so the description must carry the behavioral detail — and it does: it discloses that touching faces are not reported, that intentional overlaps appear as results, and that ignored fastener overlaps are still counted rather than dropped. The only gap is that 'They are counted' is unexplained (counted in the result set, or in a separate total?), leaving a small ambiguity about what is returned when ignore_fasteners is true.

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 purpose and key caveats before the Args block, and nearly every sentence carries information the schema does not. Minor waste exists in restating parameter names in the Args list and in the clipped final phrase 'They are counted,' which is terse at the cost of clarity.

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 read-only check tool with an output schema (so return format needn't be described), this covers purpose, matching syntax, false-positive semantics, and the fastener escape hatch. What remains unstated is only edge behavior — what happens when set_a matches nothing, or whether an assembly must be active — which is minor but not zero for a 4-parameter tool.

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?

Schema coverage is only 25% (only `instance` is documented in the schema), yet the description compensates fully for the three undocumented parameters: it gives set_a syntax with concrete examples ("DOOR:1", "Sub:1/Part:2", "*BRACKET*"), defines set_b as the same syntax with empty meaning everything else, and explains ignore_fasteners as small Content Center members under 150 mm. That is meaning an agent could not derive from the bare string/boolean types.

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 (check overlap between occurrences of the active assembly) and immediately scopes the result set: full paths, volume, and bounding box of each, with touching faces excluded. That scope statement alone distinguishes it from geometry/sketch checking siblings such as check_sketch or check_manufacturability without opening their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is real interpretive guidance — 'Intended overlaps (gasket compression, thread in thread) show up too — read the volume and bbox' tells the agent not to treat every hit as a defect, and the ignore_fasteners arg explains when to suppress fastener noise. However, there is no explicit statement of when to reach for this tool versus alternatives, and no prerequisites (e.g., an assembly must be the active document) are spelled out.

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