Skip to main content
Glama
AutoCAD MCP

AutoCAD MCP

select_entities

Select AutoCAD entities by layer, entity type, or area, and return their handles so other tools can edit them.

Instructions

Выбрать объекты по фильтру и вернуть их handle (для правки другими инструментами). Фильтр: layer (шаблон, напр. 'WALL*'), entity_type (тип DXF: LINE, LWPOLYLINE, CIRCLE, ARC, TEXT, MTEXT, DIMENSION, INSERT, HATCH...; через запятую), area [x1,y1,x2,y2] (целиком внутри; crossing=True: касается).

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": "select_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNo
layerNo
crossingNo
entity_typeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden. It does convey useful behavior beyond the schema: that handles are returned for downstream editing, and the crucial distinction between area selection as fully-inside versus crossing=True as touching. It omits whether the operation is purely read-only, any result-count or pagination limits, and whether returned handles stay valid across subsequent calls.

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?

One front-loaded sentence with the action first, the return contract second, and the filter semantics compactly attached. The parenthetical examples earn their place by disambiguating wildcard syntax and DXF type names; there is no filler.

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?

Four parameters, all addressed in the description, plus an output schema so return values need not be explained textually. For a read-only selection tool this is close to sufficient; the missing pieces are the no-filter fallback and any result-limit behavior, which matter when an agent selects across a large drawing.

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 largely does: layer is a wildcard pattern with a concrete example ('WALL*'), entity_type is a comma-separated DXF type list with enumerated examples, area is a four-value coordinate box, and crossing flips containment to intersection. The only gap is that default/null behavior (e.g. no layer = all entities) and the area coordinate ordering are left implicit.

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?

States a specific verb and resource ("Выбрать объекты по фильтру") and adds the non-obvious payload: it returns handles usable by other editing tools. That return-value framing makes the tool's role clear without having to inspect the schema. It does not explicitly contrast itself with list_entities or array_entities, which are the nearest siblings.

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?

The phrase "для правки другими инструментами" implies the intended workflow: select first, then pass the handles to transform/erase tools. However, there is no explicit when-to-use versus when-not-to-use guidance, no mention of choosing this over list_entities, and no statement of what happens with zero filters or zero matches.

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