Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_undo

Destructive

Revert recent edits to the current BricsCAD drawing by specifying 1–100 undo steps, returning how many steps were undone.

Instructions

Undo the last edits to the current drawing. Returns how many steps were undone.

One step is one successful edit tool call. Edits made through bricscad_run_lisp have no step of their own, so they go back with the step before them. steps: how many steps to undo, from 1 to 100. It stops at the oldest step.

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": "bricscad_undo"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNo
timeoutNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, and the description goes well beyond them by explaining the step granularity model and the important edge case that edits made through bricscad_run_lisp have no step of their own and are reverted together with the preceding step. It also states the range limit (1 to 100) and that undo stops at the oldest step. It stops short of covering what happens with no history or whether undo history survives a save/reopen.

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

Conciseness5/5

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

The core action and return value are front-loaded in the first sentence, followed by the step-model caveat and parameter detail; every sentence earns its place and there is no filler. Sizing is proportionate to a two-parameter tool.

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?

With an output schema present, return values need not be expanded, and the destructive annotation covers the safety profile; the description still adds the needed step-granularity semantics. The only material omission is the undocumented 'timeout' parameter, which is minor but real.

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 description coverage is 0%, so the description must carry the load: it does document 'steps' well, giving its range, default-ish behavior, and stopping condition. However, the second parameter 'timeout' is never mentioned anywhere, leaving one of two parameters completely undocumented.

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 ('Undo the last edits to the current drawing') plus the return value ('Returns how many steps were undone'), which is unambiguous and unlike any sibling such as bricscad_list_versions or bricscad_save_drawing. It also defines the unit of work ('One step is one successful edit tool call'), so an agent knows exactly what the operation acts on.

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 only implied: the tool is obviously meant to be called after edits made via the create/modify/erase tools, but there is no explicit statement of when to use it, when not to, or which alternative (e.g., restoring via bricscad_list_versions) exists. The interaction rule with bricscad_run_lisp is a solid partial substitute for real guidance.

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