Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_query_entities

Read-only

Find and filter entities in the current drawing by type, layer, block, layout, or bounding box, returning handles, types, layers, layouts, and bounding boxes for audits and selection.

Instructions

Find entities in the current drawing. Returns handle, type, layer, layout and bounding box. Up to 2000 per call.

types: DXF names such as ["LINE", "CIRCLE"]. layer, block: names, which may use the wildcards * and ?. A dynamic block goes by its own name. bbox: [min_x, min_y, max_x, max_y]; entities overlapping it match. layout: "Model" or a layout name.

An entity with no extent, such as an insert of an empty block, returns a null bounding box.

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": "bricscad_query_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
bboxNo
blockNo
layerNo
limitNo
typesNo
layoutNo
offsetNo
timeoutNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description earns credit for adding real behavior beyond that: a 2000-per-call cap and the edge case that entities with no extent (e.g. an insert of an empty block) return a null bounding box — a non-obvious result shape an agent would otherwise misread.

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?

Purpose and return shape are front-loaded, then filters are listed in a scannable per-parameter format with zero filler sentences. The trailing note about null bounding boxes is well-placed as an edge-case caveat rather than padding.

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?

An output schema exists, so the brief return-field mention is a bonus rather than a requirement. The gap is pagination: with a documented 2000-result ceiling and an undocumented 'offset' parameter, an agent has no instruction on how to page through results that exceed the cap, which matters for a query tool over large drawings.

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 coverage is 0%, so the description carries the burden and it does explain 5 of 8 parameters well, including wildcard support for layer/block, the '[min_x, min_y, max_x, max_y]' bbox ordering with overlap semantics, and the special 'Model' layout value. However, 'offset' (pagination) and 'timeout' are never mentioned, and the relationship between the 2000 cap and the 'limit' parameter (default 200) is left ambiguous.

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 ('Find entities in the current drawing') and even enumerates the returned fields (handle, type, layer, layout, bounding box), so the agent knows exactly what comes back. It stops short of distinguishing itself from siblings like bricscad_get_entity (single entity) or bricscad_find_text, which would have made it a 5.

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?

Usage is only implied through the filter semantics (types/layer/block/bbox/layout), which tells an agent how to narrow a query but not when to prefer this tool over bricscad_get_entity, bricscad_find_text, or bricscad_list_blocks. No explicit when-to-use or when-not guidance is given.

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