Skip to main content
Glama
civil-qto-mcp

civil-qto-mcp

compare_qto_with_boq

Cross-check CAD QTO measurements against Excel BoQ items by normalizing construction units and flagging differences beyond tolerance thresholds.

Instructions

[STEP 3D of HITL Workflow] Deterministically cross-check CAD QTO measurements against Excel BoQ items.

Automatically normalizes construction unit synonyms and scale factors:
- Length: `m` == `fm` == `lm` == `folyóméter`, `km` == `1000 m`, `cm` == `0.01 m`, `mm` == `0.001 m`
- Area: `m2` == `m²` == `nm` == `sqm`, `ha` == `10,000 m2`
- Volume: `m3` == `m³` == `lm3` == `bm3` == `tm3` == `cum`
- Count: `pcs` == `db` == `darab` == `akna` == `klt` == `készlet` == `nr` == `ea`

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_xlsx": "<file_path_xlsx>",
      "qto_records": "<qto_records>"
    },
    "name": "compare_qto_with_boq"
  }
}

Input Schema

NameRequiredDescriptionDefault
qto_recordsYesList of deterministic CAD QTO measurements (with qto_id, measured_quantity, measured_unit, and target item_number/row/keyword).
sheet_namesNoOptional list of visible worksheet names to search within the BoQ.
file_path_xlsxYesPath to the .xlsx or .xlsm Bill of Quantities file.
critical_percentNoPercentage threshold above which a difference is classified as CRITICAL_DISCREPANCY (default 10.0%).
tolerance_percentNoPercentage threshold within which a difference is classified as WITHIN_TOLERANCE (default 2.0%).

Output Schema

NameRequiredDescriptionDefault
comparisonsNo
discrepancy_countYes
total_comparisonsYes
missing_or_incompatible_countYes
exact_or_within_tolerance_countYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description must carry behavioral disclosure. It usefully states that matching is deterministic and that units are auto-normalized across four families, which is genuine behavior beyond the schema. However, it never says whether the .xlsx file is read-only or modified, how precedence works between target_row_number, target_item_number, and keyword_query, or what happens to measurements that match nothing.

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 determinism are front-loaded in a single sentence, followed by a scannable bulleted breakdown of normalization rules. The synonym lists are dense but each entry carries matching-relevant information; slightly tighter grouping would remove some repetition without losing content.

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-value description is correctly omitted, and all five parameters are documented in the schema. What is missing for a comparison tool of this complexity is the matching-resolution logic (which target field wins, how keyword matching behaves) and whether the BoQ file is mutated — questions an agent would need answered before invoking it.

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 100%, so the baseline would be 3, but the description adds real meaning: it enumerates accepted unit synonyms per dimension (m/fm/lm/folyóméter, ha == 10,000 m2, etc.), which tells the agent what measured_unit strings will resolve rather than fail. It adds nothing about the tolerance/critical thresholds beyond what the schema already states.

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?

The description names a specific verb and two concrete resources: cross-checking CAD QTO measurements against Excel BoQ items, tagged as 'STEP 3D of HITL Workflow'. The unit-normalization bullets further pin down what 'cross-check' means here, so an agent can distinguish it from siblings like compare_drawing_and_boq_revisions or inspect_and_audit_boq_xlsx.

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 '[STEP 3D of HITL Workflow]' tag implies sequencing (this runs after QTO extraction and BoQ inspection), which is real but implicit usage guidance. There is no explicit statement of when to choose this instead of a sibling comparison tool, nor any exclusion of cases where it should not be used.

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