Skip to main content
Glama
AutoCAD MCP

AutoCAD MCP

add_table

Creates a table at a specified top-left coordinate from row data, with optional headers, title, column widths, and text height for AutoCAD or DXF drawings.

Instructions

Таблица от левого верхнего угла (x,y): rows [[...],...], header (заголовки колонок), title, col_widths (мм, иначе по тексту), text_height (иначе авто). В COM родная таблица AutoCAD, в ezdxf линии+текст.

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": {
      "x": "<x>",
      "y": "<y>",
      "rows": "<rows>"
    },
    "name": "add_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYes
yYes
rowsYes
titleNo
headerNo
col_widthsNo
text_heightNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.3/5.0
Behavior3/5

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

With zero annotations the description carries the full burden, and it does disclose an important behavioral trait: output differs by backend (native AutoCAD table object under COM, plain lines+text under ezdxf), which affects downstream editing/explodability. It omits layer/block placement rules, what happens on invalid rows, and whether the created entity is returned or selectable.

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?

A single dense sentence front-loads the anchor and then walks the parameters in schema order, matching the input shape. Some parenthetical phrases ('иначе авто') are terse to the point of ambiguity, but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter drawing tool with no annotations, the description covers geometry and sizing well and needs not explain return values because an output schema exists. It still lacks usage context and failure/placement behavior, leaving the agent with an incomplete operational picture.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate, and it does: it clarifies that x,y is the top-left anchor (not center or baseline), that rows is a nested list, that header holds column headings, that col_widths is in millimetres with a text-derived default, and that text_height defaults to auto. Minor gaps remain on row-value typing and header alignment.

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 names a specific verb+resource (create a table anchored at the top-left corner x,y) and enumerates what the table consists of (rows, header, title, widths). It is clearly distinct from line/text drawing siblings, though it never states the intended use case (e.g. schedules, legends).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to choose add_table over draw_rectangle plus draw_text or over draw_mtext, nor any prerequisites. The only conditional text concerns internal rendering per backend, not tool selection.

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