Skip to main content
Glama

convert_drawing

Convert CAD drawings or working copies to DXF, DWG, JWW, PDF, SVG, PNG, STL, OBJ, STEP, or GLB and save outputs with a loss report.

Instructions

Convert a drawing (or its working copy) and save the outputs in the output folder (zumen-gate-out by default). Returns the saved paths and the main losses. Uses 1 call; writing JWW, DWG, SFC, P21 or STEP uses 10, and without enough paid calls returns only a preview and the loss report.

to: dxf, dwg, jww, sfc, p21, pdf, svg, png, ir, or for 3D models stl, obj, step, glb. version: the output version (e.g. a DWG version). scale: the output scale like "1/100". pages: for PDF input, pages like "1-3". A conversion longer than 40 s returns a job_id; call get_job with it.

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": {
      "path": "<path>",
      "to": "<to>"
    },
    "name": "convert_drawing"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes
pathYes
pagesNo
scaleNo
out_dirNo
versionNo
use_editsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With only openWorldHint supplied, the description carries behavioral weight well: it discloses a cost model (1 call vs 10 for JWW/DWG/SFC/P21/STEP), degraded behavior without paid calls, the default output folder, and the 40-second async handoff to get_job. It stops short of saying whether existing files in the output folder are overwritten.

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

Conciseness3/5

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

The action, destination, and format list are front-loaded, which is right, but the middle sentences are run-on and mix cost, failure, and return values in one breath ('Uses 1 call; writing JWW... uses 10, and without enough paid calls returns only a preview...'). The parameter glossary at the end is useful but sits after the operational detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter conversion tool with no output schema and minimal annotations, the description covers returns ('saved paths and the main losses') and the async path, which is a lot. It is still missing overwrite semantics for out_dir and the meaning of use_edits, both of which affect how the call is made.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for four of seven parameters (to with an enumerated format list, version, scale, pages). It leaves path, out_dir, and especially use_edits ('working copy' is only implied) unexplained, so an agent must guess what toggling use_edits actually changes.

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?

The description opens with a specific verb and resource ('Convert a drawing (or its working copy)') and adds the destination and return content, so the agent knows exactly what operation runs. It never names a sibling such as render_drawing or edit_drawing, so the reader must infer the boundary between converting and rendering/editing.

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?

It gives concrete conditional guidance: formats that cost 10 calls, the fallback when paid calls are insufficient (preview plus loss report), and the >40 s case that returns a job_id to be passed to get_job. That is a real decision path, but there is no statement of when to prefer this tool over edit_drawing or render_drawing.

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