Skip to main content
Glama
inventor-mcp-server

inventor-mcp-server

shell

Hollows the active part's first body into an even-thickness wall for housings, cups, or boxes, leaving selected faces open; specify wall thickness and inside/outside direction.

Instructions

Hollow the active part's first body into a wall of even thickness — a housing, cup or box — leaving the chosen faces open. For sheet metal use add_sheet_metal_face and add_flange.

Pick the open faces with find_faces (e.g. normal=[0,0,1] for the top) right before this call. Returns the feature name and the change: a shell removes volume; a wall too thick for the body fails.

Args: thickness: Wall thickness in mm. remove_faces: Comma-separated face numbers from find_faces to leave open, e.g. "5". Empty = a closed hollow body. direction: "inside" (the outer size stays), "outside" or "both".

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "shell"
  }
}

Input Schema

NameRequiredDescriptionDefault
instanceNoWhich connected Inventor to use (list_instances). Leave empty when only one is connected.
directionNoinside
thicknessNo
remove_facesNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.0

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does: it discloses the return (feature name plus the change), the volumetric effect (shell removes volume), and a concrete failure mode (a wall too thick for the body fails). The sequencing dependency on find_faces is a behavioral trait not expressible in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and scope, then alternatives, then the prerequisite, then behavior and failure mode; the Args block is compact and every clause carries information. No filler or restated title.

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 mutation tool with no annotations, the description covers prerequisites, failure modes, and the geometric outcome; an output schema exists so return-value detail is unnecessary. It stops short of stating any permission or reversibility characteristics, which is the only remaining 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 25%, so the description must compensate and largely does: it gives units for thickness (mm), the format and empty-value behavior for remove_faces (comma-separated face numbers, empty = closed hollow body), and the three direction values with the meaning of 'inside'. Only the instance parameter is left to the schema.

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 ('Hollow the active part's first body into a wall of even thickness'), names the scope (active part, first body), and explicitly distinguishes the sheet-metal case to sibling tools add_sheet_metal_face and add_flange. The housing/cup/box examples make the geometric intent concrete.

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

Usage Guidelines5/5

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

Explicitly routes agents away from this tool for sheet metal, and states a prerequisite ordering constraint: pick open faces with find_faces immediately before this call (with a normal=[0,0,1] example). It also explains the direction choice semantics (inside keeps outer size).

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