Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_batch_run

Destructive

Run one job across many drawings, one at a time, and return a result per file. Use dry_run first to preview files, outputs, and naming before writing anything.

Instructions

Run one job on many drawings, one at a time, and report a result per file. Try dry_run first.

job: {"type": ...} with its options. audit and find_text write nothing. export_dxf, plot_pdf (layout "*" plots every sheet to -.pdf), save_as and lisp with save=true write .dxf, .pdf or .dwg into output_folder. lisp runs code in each drawing and returns its value. files or folder: the drawings, up to 500. folder takes a glob pattern, and recursive for subfolders. Sources open read-only. A source is replaced only when output_folder is its own folder and overwrite=true. Drawings already open in BricsCAD are refused. timeout: seconds per file. A timeout stops the batch, since a dialog may be blocking BricsCAD. Afterwards the current drawing may be another open drawing.

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": {
      "job": "<job>"
    },
    "name": "bricscad_batch_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYes
filesNo
folderNo
dry_runNo
patternNo*.dwg
timeoutNo
overwriteNo
recursiveNo
output_folderNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior3/5

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

The description is unusually informative for a destructive tool: it states the exact condition under which a source file is overwritten (output_folder must be the source's own folder AND overwrite=true), that sources otherwise open read-only, that already-open drawings are refused, that a per-file timeout halts the whole batch because a dialog may be blocking, and that the current drawing may change afterwards. Annotations already declare destructiveHint=true, so this is added context rather than novel safety disclosure.

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?

Packed and front-loaded — the core action and the dry_run warning come first, then ordered specifics. The telegraphic fragments ("job: {\"type\": ...} with its options.") and inconsistent sentence style cost some readability, but for a nine-parameter polymorphic tool almost every clause carries unique information.

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?

An output schema exists, so return values need not be described, and the remaining complexity — batch iteration, file selection, overwrite safety, timeout behavior, state after the call — is all addressed. Nothing an agent needs in order to invoke this correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does: it covers all nine parameters plus the job discriminator, explains files vs folder (up to 500, glob, recursive subfolders), timeout semantics (seconds per file, batch-stopping), overwrite/output_folder interaction, and job-specific options such as layout "*" fanning out to <name>-<sheet>.pdf and the output naming patterns.

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?

"Run one job on many drawings, one at a time, and report a result per file" gives a specific verb (run a job), a specific scope (many drawings, serially, per-file results), and immediately implies the batch-vs-single distinction that separates it from the single-drawing siblings. The follow-on enumeration of job types makes the resource scope concrete.

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 front-loads an operational recommendation ("Try dry_run first") and explicitly separates job types by side effect: audit and find_text write nothing, while export_dxf, plot_pdf, save_as and lisp-with-save write files. It does not explicitly say "for a single drawing use bricscad_run_lisp instead of this," so the alternative-selection guidance is implied rather than stated.

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