Skip to main content
Glama
civil-qto-mcp

civil-qto-mcp

compare_drawing_and_boq_revisions

Compare old and new CAD drawings and BoQ workbooks to calculate area, linear, point and row-level differences and generate variation order payloads.

Instructions

[v0.5 Tool 17] Compare Old vs. New (or Design vs. As-Built) CAD drawings and/or BoQ Excel workbooks,
calculating spatial area additions/removals (`New - Old` and `Old - New`), linear/point deltas,
row-level BoQ diffs, and ready-to-apply variation order (`kiv. észrevétel` / `K-tétel`) payloads.

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": "compare_drawing_and_boq_revisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoLanguage for generated variation order notes ('en', 'de', or 'hu').hu
sheet_namesNoOptional list of visible BoQ worksheet names to compare.
new_cad_pathNoOptional path to the New / Revised (R1) or As-Built (Megvalósulási) DXF or DWG drawing.
old_cad_pathNoOptional path to the Old / Design (R0) DXF or DWG drawing.
point_layersNoPoint/circle/insert layers to compare between Old and New CAD drawings.
linear_layersNoLinear layers to compare between Old and New CAD drawings.
boundary_layersNoPolygon area layers to compare between Old and New CAD drawings.
new_boq_xlsx_pathNoOptional path to the New / Revised BoQ Excel workbook (.xlsx).
old_boq_xlsx_pathNoOptional path to the Old / Baseline BoQ Excel workbook (.xlsx).
unit_scale_to_meterNoCAD drawing unit scale to meters (default 1.0).

Output Schema

NameRequiredDescriptionDefault
warningsNo
new_boq_pathNo
new_cad_pathNo
old_boq_pathNo
old_cad_pathNo
boq_item_diffsNo
boq_added_countNo
cad_layer_diffsNo
boq_removed_countNo
boq_modified_countNo
boq_net_total_deltaNo
new_boq_grand_totalNo
old_boq_grand_totalNo
ready_variation_itemsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose the computation semantics (delta direction New - Old and Old - New, row-level BoQ diffs, generated variation order notes) and that a locale governs note language, but it never states that all ten parameters are optional or whether at least one old/new path pair must be supplied, nor whether this is a read-only analysis or produces files. For a zero-required-parameter tool that is a real gap.

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?

Two sentences, front-loaded with the core comparison, and each clause adds a distinct output category. The leading '[v0.5 Tool 17]' version tag is pure noise and the parenthetical multilingual note adds clutter, but neither obscures the main statement.

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 return values need not be explained, and the schema documents all ten parameters. However, for a flexible 10-parameter tool with zero required fields and no annotations, the description should state the minimum viable invocation (e.g. supply at least one old/new CAD pair or BoQ pair) and what happens when only one side is given; that omission leaves real ambiguity.

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%, so the schema already documents every parameter, and the baseline is 3. The description adds only the conceptual mapping of old to Design/R0 and new to Revised/R1/As-Built plus the fact that boundary layers feed area math while linear and point layers feed the other deltas; it does not explain layer interaction, sheet_names filtering, or unit_scale_to_meter behavior beyond the schema.

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 uses a specific verb (compare) over specific resources (CAD drawings and BoQ Excel workbooks) and enumerates the concrete outputs: area additions/removals in both directions, linear/point deltas, row-level BoQ diffs, and variation order payloads. That is enough to distinguish it from a pure QTO or pricing tool. It stops short of naming any sibling, so an agent must still infer how it differs from compare_qto_with_boq.

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 parenthetical 'Old vs. New (or Design vs. As-Built)' implies the revision-comparison scenario, but there is no explicit when-to-use statement, no when-not, and no named alternative such as compare_qto_with_boq or apply_boq_modifications_and_pricing. An agent can infer the context but is not routed anywhere.

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