Skip to main content
Glama
inventor-mcp-server

inventor-mcp-server

save_document

Save the active Inventor document without a dialog, optionally saving changed dependents while skipping library and Content Center files to avoid rewriting shared parts.

Instructions

Save the active document — never opens a dialog, and never writes a library or Content Center file. Dependents that changed (e.g. sub-assemblies, edited parts) are saved one by one first, except files in the project's library paths or Content Center folders and Content Center members: Inventor marks standard parts dirty after opening an old assembly, and re-saving them would rewrite shared library files. Returns the files saved and the ones skipped. The path is checked first (characters, extension, an existing file) so a bad one gets a clear message instead of Inventor's E_INVALIDARG.

Args: path: Full file path to save as (e.g. "D:/parts/flange.ipt"). If empty, saves in place. overwrite: Replace a file that already exists at path (not one open in Inventor). save_dependents: False = save only this document (Save2(False)); changed dependents stay unsaved and are listed.

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": "save_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
instanceNoWhich connected Inventor to use (list_instances). Leave empty when only one is connected.
overwriteNo
save_dependentsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.0
    • changedInput schema / properties / save_dependents / default
      Previous value: -trueNew value: +false
  2. First observedv0.8.0

TDQS

A3.8/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does so well: it discloses that no dialog opens, that dependents are saved one-by-one before the main document, that library/Content Center files are skipped to avoid rewriting shared parts, and that the return value lists saved vs skipped files. It does not cover failure cases such as a document never saved before or read-only files, which keeps it short of 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 core behavior and its non-obvious guardrails are front-loaded in the first paragraph, and the Args block adds semantics the schema lacks. Mild redundancy with the schema titles in the Args section costs a point but nothing is filler.

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?

A mutation tool with no annotations and no output schema explanation needed (an output schema exists), so the description must carry safety and side-effect context — it does, via dependency ordering, library-skip rationale, and path pre-validation. Lacking any statement about required connection/permissions or whether a failure leaves partial saves is the 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% (just the instance param), but the description supplies real semantics for the other three: path meaning plus empty-means-save-in-place, overwrite excluding files open in Inventor, and save_dependents mapping to Save2(False) with the consequence that changed dependents stay dirty and get listed. Only the interaction between path and overwrite on validation order is left slightly implicit.

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+resource (save the active document) and immediately bounds scope: no dialogs, no library or Content Center writes. It is clear what the tool does, but it never names a sibling (e.g. export_document, manage_documents) as the alternative for other save/export needs.

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?

Usage is implied through behavior: save-in-place when path is empty, dependency saving controlled by save_dependents, and library/Content Center files deliberately skipped. There is no explicit 'use this when / use X instead' routing, so the agent must infer when this beats export_document or manage_documents.

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