Skip to main content
Glama

MIDAS CIVIL NX tools (MIDAS IT Europe)

Model health check (QC + results benchmarks)

model_health_check
Read-only

Use for "is anything wrong with my model?". This is the full check: it runs model_qc_check's fourteen checks plus units, tendons, stages, moving loads and results. Prefer it to model_qc_check. One read-only check of the open CIVIL NX model for anything that is likely wrong, grouped into areas with a red/amber/green status each. DATA (no analysis needed): the Model Report's fourteen QC checks plus warped / badly shaped plates, plates facing the other way from their neighbours, nodes lying on an element without being joined to it (mesh cracks, beams resting on girders unconnected), beam lines that flip direction or whose beta angle jumps, material values out of range (unit slips), sections with zero area or inertia, plates with no thickness, rigid and elastic links that cannot work, supports holding nothing, self weight missing / upward / counted twice in a combination, upward dead loads, load values 1000× out of line, beam loads on plates, moving loads with no lanes or vehicles, construction stages (elements never activated, loads on parts not yet built, stages with no supports, activation order), combinations (cycles, unfactored ULS, duplicates, cases never combined), empty or unused groups, and tendons that cannot be stressed. UNITS (typing slips): creep/shrinkage and strength-gain inputs (fck in MPa typed into a kN/m² box, humidity as a fraction, notional size in mm in a metre model, shrinkage strains not × 10⁻⁶, strength not matching the linked concrete grade), tendon area / strengths / duct diameter / anchorage slip, thermal coefficients, temperatures, section depths and plate thicknesses. TENDONS: cover — every profile point placed on its girder and compared with the section's top and soffit (outside the concrete, with the likely coordinate slip: mm in a metre model or the sign of z; clear cover under 50 mm); jacking stress against min(0.8 fpk, 0.9 fp0.1k) and slips, duct area against the steel, friction μ and wobble ranges, friction loss estimated from each profile, sharp bends, profiles longer than their elements, tendons on elements that do not join up. MOVING LOADS (Eurocode EN 1991-2 and CS 454 / CS 458 rules): the moving-load code against the vehicles and cases; cases naming lanes or vehicles that do not exist, vehicles with no sub-type; duplicate names; lane widths against the code (Eurocode 3.0 m notional lanes or w/2 on 5.4–6 m; CS 454 3.0 m single / 2.5 m convoy, matched to the case's vehicle; SV lanes at least the vehicle width) with the slip named; remaining areas wide enough for another lane, ALL model 2 lane count and equal widths; lanes overlapping in one case; wheel spacing against the vehicles (BS stores a third, Eurocode the real value) and the lane; lanes off the deck (ECC sign flipped, mm in a metre model); lane element paths; Eurocode ψ — 'Ignore ψ factor' against a case named frequent / characteristic, ψ 0 or above 1, railway ψ1, and whether there are both characteristic and frequent LM1 cases; α factors (UK NA half entered), βQ and footway load; CS 458 SV speed against DAF, HB units. STAGES (set-up): creep/shrinkage links that reach no concrete or are switched off, activation ages under 1 day, too short a final stage, composite-section stages. RESULTS (when the model has been analysed): for every static load case the sum of reactions against the total applied load (equilibrium), the self-weight reaction against Σ density × element volume, displacements too large to be real (mechanisms, unit slips), and reaction symmetry on a symmetric model; on a construction-stage model, stages the analysis did not reach, stage displacements, and each stage's reactions against the weight and loads active then. Each with the numbers. Returns each check's result (pass / fail / not applicable / not run), severity, criterion and the ids involved. Reads only: GET /db tables, /ope/SECTPROP and POST /post/TABLE (REACTIONG, DISPLACEMENTG). On the website it runs as a job. Use model_qc_check for the plugin's fourteen checks alone, in another language.

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": "model_health_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
partsNoWhich checks to run: data (model tables) and/or results (needs an analysed model). Default both.
maxIdsNoIds listed per check.
maxNodesNoMost nodes to read displacements at; a larger model is sampled evenly.
thresholdsNoOverride the limits the checks use (defaults in brackets).
toleranceMmNoNodes closer than this (mm) count as coincident; also the distance at which a node counts as lying on an element.
displacementsNoRead nodal displacements for the displacement check (one table read per 2000 nodes × 10 load cases).
outlierFactorNoElement length outlier factor (the Model Report check).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / thresholds / properties / ductRatio
      Added value: +{
      +  "description": "Smallest duct area / strand area for internal bonded tendons [2].",
      +  "type": "number"
      +}
    • addedInput schema / properties / thresholds / properties / frictionLossPct
      Added value: +{
      +  "description": "Warn when a tendon's estimated friction loss exceeds this, % [30].",
      +  "type": "number"
      +}
    • addedInput schema / properties / thresholds / properties / laneOutsideDeck
      Added value: +{
      +  "description": "Flag a traffic lane whose centre lies more than this beyond the outermost deck line, m [0.5].",
      +  "type": "number"
      +}
    • addedInput schema / properties / thresholds / properties / minCoverMm
      Added value: +{
      +  "description": "Smallest clear cover from a tendon duct to the section's top or soffit, mm [50].",
      +  "type": "number"
      +}
    • addedInput schema / properties / thresholds / properties / minTendonRadius
      Added value: +{
      +  "description": "Tightest allowed tendon bend radius, m [2.5].",
      +  "type": "number"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint it discloses the exact backend calls (GET /db tables, /ope/SECTPROP, POST /post/TABLE), the response shape per check (pass / fail / not applicable / not run, severity, criterion, ids), and that it runs as a job on the website. The costly displacement read is surfaced in the displacements parameter, so the agent can predict runtime cost. Nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the sibling preference are front-loaded, but the body is a multi-thousand-character enumeration of individual checks that the agent cannot act on and that mostly belongs in documentation. There is also redundancy: the model_qc_check alternative is stated twice, once at the start and again in the final sentence.

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 wide, seven-parameter, nested-object tool with no output schema, the description supplies the missing return contract (per-check status and severity), the read-only backend surface, the analysed-model prerequisite for results, and the cost model. An agent has everything needed to decide whether to run it and how to interpret the output.

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 already 100% with per-threshold defaults, so the baseline is 3; the description adds meaning by partitioning the work into the DATA / UNITS / TENDONS / MOVING LOADS / STAGES / RESULTS groups that the parts and thresholds parameters select between. It does not, however, explain how parts interacts with thresholds or what happens when results is requested on an unanalysed model.

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?

Opens with a concrete agent-facing question ("is anything wrong with my model?") and states the specific scope: the full check = model_qc_check's fourteen checks plus units, tendons, stages, moving loads and results. It explicitly distinguishes itself from the sibling model_qc_check, so an agent can choose between them without opening either schema.

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?

Gives an explicit preference ("Prefer it to model_qc_check") plus the inverse routing rule ("Use model_qc_check for the plugin's fourteen checks alone, in another language"), and scopes the results half to "when the model has been analysed". When-to-use, when-to-use-the-alternative, and the precondition are all stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources