Skip to main content
Glama
civil-qto-mcp

civil-qto-mcp

inspect_civil_dxf

Inspect civil DXF drawings to detect CRS, units, layers, and geometry issues before measurement, ensuring accurate quantity takeoffs.

Instructions

[STEP 1 of HITL Workflow] Inspect a civil engineering DXF drawing before any measurement.

Returns:
- Modelspace vs. Paperspace entity counts and 3D bounding box
- 3-factor CRS & Drawing Unit estimation (auto-detects Hungarian EOV HD72 metric coordinates,
  checks $INSUNITS header mismatches, and analyzes median text heights)
- Per-layer entity type breakdown, closed/open/nearly-closed polyline counts, HATCH counts,
  distinct INSERT block names, block ATTRIB tag names, and cleaned sample texts
- CAD Hygiene Warnings (Civil 3D proxy objects, external XREFs, 3D 'Flying Z' elevation jumps,
  nearly-closed polylines, and duplicate segments)

After calling this tool, present the layer mapping and `recommended_unit_scale_to_meter`
to the user for confirmation before calling `measure_linear_and_area_features` or
`extract_utility_network_and_levels`.

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": {
      "file_path": "<file_path>"
    },
    "name": "inspect_civil_dxf"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_pathYesAbsolute or relative path to the .dxf drawing file.
max_sample_textsNoMaximum number of sample cleaned TEXT/MTEXT/ATTRIB strings to return per layer.
layer_filter_regexNoOptional case-insensitive regular expression to filter layer names (useful on drawings with 200+ layers).
ignore_empty_layersNoIf True (default), omits layers that contain 0 Modelspace entities.

Output Schema

NameRequiredDescriptionDefault
layersNo
file_pathYes
dxf_versionYes
crs_and_unitsYes
modelspace_bboxNo
cad_health_warningsNo
total_layers_returnedYes
total_modelspace_entitiesYes
total_paperspace_entities_ignoredYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does most of the work: it discloses that coordinate systems and drawing units are estimated heuristically (Hungarian EOV HD72, $INSUNITS mismatch checks, median text heights), that Civil 3D proxy objects/XREFs/'Flying Z' jumps may appear, and that a human confirmation gate is required. What it omits is the safety/performance profile — it never states that the operation is read-only with no side effects on the file, nor anything about runtime on very large drawings.

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?

Front-loaded with the workflow step and purpose, then a tightly bulleted return summary, closing with the required next action. Every line carries information; no filler or restatement of the title.

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 4-parameter, read-only inspection tool with a full output schema, the definition covers everything an agent needs: what is returned, what ambiguities the tool itself resolves (CRS, units), what hazards trigger warnings, and what must happen before the next call. Return-value detail can safely be delegated to the output schema.

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 description coverage is 100%, with every parameter documented including defaults, min/max, and the 200+ layer use case, so the baseline is 3. The description adds no parameter-level meaning beyond the schema — max_sample_texts, layer_filter_regex, and ignore_empty_layers are never mentioned in prose.

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?

States a specific verb and resource ('Inspect a civil engineering DXF drawing') and pins its scope with 'before any measurement' plus a [STEP 1 of HITL Workflow] tag. An agent can distinguish it from siblings like measure_linear_and_area_features or extract_utility_network_and_levels purely from the description.

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

Usage Guidelines5/5

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

Explicit sequencing: call before any measurement, then present layer mapping and recommended_unit_scale_to_meter to the user for confirmation before invoking measure_linear_and_area_features or extract_utility_network_and_levels. It names both the condition for use and the concrete alternatives that follow, so nothing is left to inference.

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