Skip to main content
Glama
SolidWorks MCP Python

SolidWorks MCP Python

by locense

Generate Drawing Package

generate_drawing_package
DestructiveIdempotent

Create a complete A3 drawing package for a part or assembly in one call, including standard views, dimensions, title block, overlap check, and PDF export.

Instructions

Create a complete A3 drawing of a part or assembly in one call, and save it with a PDF.

It opens a new drawing with an A3 ISO frame and fills the title block (title, number, material, weight, drawn by, date, revision). It places front, plan, side and isometric views at one standard scale, shows the model dimensions once in tidy rows, and adds view captions and a NOTES block. Then it checks nothing overlaps. Use it instead of the step-by-step drawing tools when you want the whole drawing. Needs: the model file on disk. Changes: saves <drawing_number>.SLDDRW and a PDF, replacing files of those names, and by default writes Description, Material and Weight into the model and saves it (turn off with write_model_properties). Returns: data with scale, views, dimensions, overlap_check, title_block, drawing_path, pdf_path and steps. A remaining overlap makes the call an error carrying that data; for long title-block text pass title_block_text_height_mm (e.g. 3).

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": "generate_drawing_package"
  }
}

Input Schema

NameRequiredDescriptionDefault
input_dataNoThe drawing. `model_path` (.sldprt or .sldasm) is required; `output_dir`, the title-block fields (`title`, `drawing_number`, `author`, `revision`, `company`), `notes`, `include_isometric`, `include_bom` and `write_model_properties` have defaults.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true): it names the exact files written, that same-named files are replaced, and that by default the model itself is modified and saved via write_model_properties — the precise destructive surface the annotation only flags generically. It also discloses the error behavior (a remaining overlap makes the call an error but still carries data) and enumerates the returned fields, which is unusual specificity for a mutating tool.

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 outcome, then follows a predictable What / Use instead / Needs / Changes / Returns structure that matches how an agent scans. It is dense rather than bloated, but the 'Returns: data with scale, views, dimensions...' sentence duplicates the output schema and is the one part that doesn't earn its space.

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 a single-parameter wrapper around a fairly complex drawing pipeline, it covers prerequisites, side effects, file replacement, override flags, error semantics and the return shape. With an output schema present it doesn't need to explain return values, yet doing so briefly is harmless and the rest leaves no ambiguity about what calling it does.

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 description coverage is already 100%, so the baseline is 3; the description earns above that by adding operational meaning: model_path is required, write_model_properties is the opt-out for model mutation, and 'for long title-block text pass title_block_text_height_mm (e.g. 3)' turns an abstract cap parameter into a concrete remedy. Minor loss: it doesn't touch notes/include_bom behavior beyond what the schema already says.

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 — 'Create a complete A3 drawing of a part or assembly in one call, and save it with a PDF' — and then enumerates exactly what the drawing contains (ISO frame, title block, four views, dimensions, captions, NOTES, overlap check). It explicitly contrasts itself with 'the step-by-step drawing tools', so an agent can distinguish it from siblings like add_drawing_view or create_drawing_view without opening a schema.

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?

'Use it instead of the step-by-step drawing tools when you want the whole drawing' gives a clear selection condition and an alternative class. Prerequisite is stated ('Needs: the model file on disk'). It stops short of a 5 because it never says when not to use it (e.g. when only a single view or a dimension pass is wanted), leaving that inference to the agent.

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