Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_run_lisp

Destructive

Run LISP expressions inside BricsCAD and get the last expression's value back, enabling automation and drawing edits when no dedicated tool exists.

Instructions

Run LISP in BricsCAD and return the value of its last expression.

LISP can change or delete files and start programs, so use a dedicated tool where one exists. Do not use vla-save or vla-saveas: they open a dialog or fail. Use _.QSAVE or _.SAVEAS. Do not close the only open drawing: the listener stops.

code: one or more LISP expressions. timeout: seconds to wait for an answer.

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": {
      "code": "<code>"
    },
    "name": "bricscad_run_lisp"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYes
timeoutNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior5/5

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

The annotations declare destructiveHint=true, and the description is fully consistent, adding substance the annotations cannot: the blast radius ('can change or delete files and start programs'), two known failing function families, and a session-killing failure mode. These are undocumented side effects and traps rather than a restatement of the safety flags.

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?

The rule and its risk are front-loaded in two sentences, then constraints, then the parameter glossary with no filler. The only soft spot is the vaguer 'use a dedicated tool where one exists' line, which sits alongside the far more actionable named-command warnings.

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?

An output schema exists, so return values need not be explained, and the annotations already carry the read/write profile; the description covers the remaining real risks. The one gap left is timeout behavior on expiry, which matters for an arbitrary-code executor but is a narrow omission against an otherwise strong definition.

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 compensate, and it partially does: 'one or more LISP expressions' conveys cardinality the string-typed 'code' field hides, and 'seconds to wait for an answer' supplies the unit missing from the schema. It says nothing about what the default 30 means behaviorally, or what happens when the timeout expires (error, partial result, abandoned evaluation).

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 ('Run LISP in BricsCAD') and states the return contract ('return the value of its last expression'), which no sibling name suggests. It differentiates only generically, though: 'use a dedicated tool where one exists' tells the agent to prefer siblings but names none of the 27 alternatives, so the agent must guess which ones replace this.

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?

It gives explicit when-not-to-use guidance ('use a dedicated tool where one exists'), names two concrete forbidden commands with the reason (vla-save/vla-saveas 'open a dialog or fail') and the exact substitutes (_.QSAVE, _.SAVEAS). It adds a hard boundary condition ('Do not close the only open drawing: the listener stops'), which is precisely the kind of constraint an agent cannot infer elsewhere.

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