Skip to main content
Glama
SolidWorks MCP Python

SolidWorks MCP Python

by locense

Save Assembly

save_assembly
DestructiveIdempotent

Saves the active SolidWorks assembly in place or to a new .sldasm path, optionally copying referenced parts; deprecated in favor of save_file.

Instructions

Deprecated: use save_file.

Save the active assembly in place, or as a new .sldasm, optionally copying the parts it uses alongside.

Before writing to a new path it checks the folder exists and is writable, changes the extension to .sldasm, and refuses an existing file unless overwrite is on. With include_references, it instead copies the assembly file as last saved, and the files it references, into the new folder; unsaved changes are left out and references are not updated. To copy an assembly with its referenced parts, use pack_and_go_assembly. Needs: an open, active assembly, saved once for include_references. Changes: writes the assembly file (and copies). Returns: file_path, plus copied_files and missing_source_files when copying references.

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_assembly"
  }
}

Input Schema

NameRequiredDescriptionDefault
input_dataNoThe save. Nothing is required: give `file_path` for a new path or omit it to save in place; `overwrite` and `include_references` are off.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior3/5

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

The description discloses real behavior beyond the annotations: folder existence/writability checks, extension forced to .sldasm, refusal of an existing file unless `overwrite` is on, and the caveat that `include_references` copies the last-saved file so unsaved changes are dropped and references are not updated. That is meaningful added context for a destructiveHint=true write operation, but it does not touch on failure modes, error reporting, or what the returned `file_path` points to when saving in place. Adequate-to-good, not exhaustive.

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 deprecation notice followed by purpose, then the alternative route, then prerequisites and effects – a sensible order. The middle sentences are dense and the line breaks are awkward, but no sentence is filler; the pedantic 'Needs/Changes/Returns' block is compact and useful.

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?

Returns are documented in prose (`file_path`, plus `copied_files` and `missing_source_files`) and an output schema exists, annotations cover safety hints, and the only parameter is fully described in both schema and description. For a single-parameter save tool, an agent has everything needed to call it correctly and to predict its side effects.

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 100%, and the description still adds semantics the schema lacks: `include_references` copies the assembly as last saved rather than in its current in-memory state, and only applies to a new folder target. That nuance is not derivable from the schema field text. `overwrite` behavior (refuse existing file unless set) is also clarified beyond the schema's terse 'Overwrite existing file'.

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?

Leads with a deprecation notice and names the replacement, then states a concrete verb+resource: save the active assembly in place or as a new .sldasm with optional part copying. It is clearly distinguishable from save_file (replacement) and pack_and_go_assembly (assembly-with-references copy).

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 redirects to `save_file` as the successor and to `pack_and_go_assembly` when the goal is copying an assembly with its referenced parts, plus states prerequisites (an open, active assembly; saved once for `include_references`) and the not-recommended `include_references` path. When-to-use and when-not-to-use are both covered.

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

Deploy Server

Other Tools