Skip to main content
Glama
AutoCAD MCP

AutoCAD MCP

draw_batch

Draw up to 5,000 AutoCAD objects in one command with one undo step; invalid items are skipped and returned with their reasons.

Instructions

ПАКЕТНОЕ РИСОВАНИЕ: много объектов одной командой (до 5000), один шаг отмены. items: список объектов {type, ...параметры, layer?, color?, linetype?, lineweight?}. Типы и параметры: line {x1,y1,x2,y2 | p1,p2}; polyline {points,closed}; rect {x,y,w,h}; circle {cx,cy,r}; arc {cx,cy,r,start_angle,end_angle | points:3}; ellipse {cx,cy,rx,ry,rotation}; polygon {cx,cy,r,sides}; point {x,y}; spline {points}; text {x,y,text,height?,align?,rotation?}; mtext {x,y,text,width?}; dim {x1,y1,x2,y2,offset,vertical?,aligned?,text?}; hatch {points,pattern,scale}. Ошибочные элементы пропускаются, их номера и причины возвращаются.

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": {
      "items": "<items>"
    },
    "name": "draw_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the 5000-object cap, that the whole batch is a single undo step, and critically that invalid elements are skipped rather than aborting, with their indices and reasons returned. It leaves unstated whether a drawing must be open or which units apply, but the mutation/error semantics are well covered.

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?

Front-loaded with the operation and constraints, then a compact type catalog where every token carries a parameter name. It is dense and reads as one long run-on block, but no sentence is disposable given the 0% schema coverage.

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?

For a single-parameter batching tool with an output schema, this supplies everything the agent needs: type/field grammar, shared style attributes, size limit, undo semantics, and partial-failure behavior. Return values need not be explained since an output schema exists, yet the error-reporting note adds useful context.

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 coverage is 0% and the schema types items only as an untyped array of objects, so the description does all the work. It enumerates every supported shape type with the exact field names and optional overrides (layer, color, linetype, lineweight), fully compensating for the empty schema.

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?

The description opens with a specific verb+resource ('ПАКЕТНОЕ РИСОВАНИЕ: много объектов одной командой') and immediately differentiates itself from the single-shape siblings by stating the batch scope and 5000-object ceiling. An agent can tell this from draw_line or draw_circle without opening any schema.

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 clear context for selecting it (many objects in one command, one undo step, up to 5000), which implies the batch alternative to the individual draw_* tools. It stops short of explicitly naming those siblings or stating exclusions (e.g. 'use draw_line for a single entity').

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