Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_modify_entities

Destructive

Modify BricsCAD entities by handle: move, rotate, scale, recolor, change layer or linetype, and replace text in one all-or-none operation that rejects locked layers.

Instructions

Change entities by handle. Changes all of them or none, and refuses locked layers.

move: a displacement, [dx, dy] or [dx, dy, dz]. rotate: {"angle": degrees, "base": point}. scale: {"factor": number above 0, "base": point}. layer: an existing layer. color: 0 by block, 1 to 255, or 256 by layer. linetype: loaded from iso.lin if the drawing does not have it yet. text: new text for TEXT, MTEXT or MULTILEADER. Change attributes with bricscad_set_attributes. MTEXT and MULTILEADER text takes format codes, where \P is a line break. Write a literal backslash or brace as \, { or }.

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": {
      "handles": "<handles>"
    },
    "name": "bricscad_modify_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
moveNo
textNo
colorNo
layerNo
scaleNo
rotateNo
handlesYes
timeoutNo
linetypeNo

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 readOnlyHint=false and destructiveHint=true, so the description doesn't need to re-state that this mutates. It adds real value beyond them: the operation is atomic ("all of them or none"), it refuses locked layers, and a missing linetype is auto-loaded from iso.lin — a side effect the annotations could never convey.

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?

Atomicity and the locked-layer refusal are front-loaded in the opening sentence, then each option gets one labeled line — easy to scan and each line earns its place. The escape-sequence note for literal backslash and brace is slightly verbose but prevents a real formatting error.

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 no explanation, and the annotations cover the safety profile. For a 9-parameter mutation tool the description covers the semantically tricky options well, leaving only the timeout and the handle-list semantics implicit.

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% across 9 parameters, so the description carries the full burden and largely meets it: move accepts 2D or 3D displacement arrays, rotate takes degrees plus a base point, scale takes a positive factor plus a base point, color encodes 0=by block / 1-255 / 256=by layer, and MTEXT format codes are spelled out. Only handles and timeout go unexplained.

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?

"Change entities by handle" gives a specific verb and resource plus the key scoping constraint (handles, not filters). It also carves out attribute editing to bricscad_set_attributes, so an agent can tell the two apart. It stops short of distinguishing this from create/erase/query, but the mutation scope is unmistakable.

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?

There is one explicit routing rule: use bricscad_set_attributes for attributes rather than the text property. Usage is otherwise implied by the property list, with no statement of when to prefer bricscad_create_entities or bricscad_erase_entities, or any prerequisite about valid handles.

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