Skip to main content
Glama

immobilier

by fr.synergieloc
OverviewDiscussionsAdmin

cao_ids_verifier

WHEN a BIM manager's information requirements (an IDS 1.0 file, buildingSMART) must be checked on a model before delivery — ours built from the scene, or an architect's IFC: checks every specification (entity, attribute, property compared in SI units, classification, material, partOf; required, optional, prohibited; target IFC version) and returns, per specification, the applicable elements and those failing with their reasons; bcf: true adds the failures as BCF 2.1 topics with their objects. Without ids, checks our French housing IDS (rooms with net, habitable and Carrez areas, typed doors and windows, accessibility, load-bearing walls with materials, storeys, stairs, Lambert-93), free at GET /api/v1/cao/ifc/ids/logement-fr.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bcfNoTrue to add the failures as a BCF 2.1 zip in base64 (bcf_base64).
idsNoOptional IDS 1.0 XML text; default: our French housing IDS.
ifcNoOptional IFC text (STEP) to check instead of the scene; an architect's model keeps its GlobalIds.
mursNoWalls: plan segments extruded vertically. Every coordinate in this whole scene is in MILLIMETRES, in a single plan frame whose origin you choose — X to the right, Y upward, Z up from the floor. Keep one consistent origin across murs/boites/plan: the generators never recentre anything for you.
planNo2D reference lines — drawn flat, never extruded and never counted in the quantities. Use them for axes, plot limits or setting-out marks.
boitesNoBoxes (furniture, volumes): a rectangular block placed by its CENTRE, not by a corner. Millimetres, same frame as murs[].
georefNoOptional Lambert-93 (EPSG:2154) false origin for IfcMapConversion. Local millimetres are scaled by 0.001 to CRS metres. Do not invent coordinates: omit est/nord if unknown (origin stays 0). orientation is the angle in degrees of project X from map East, counterclockwise.
cerclesNoCircles on the 2D plan, alongside plan[] lines: each has a centre and a radius, in the same unit as the plan. Use for round shapes a polyline would render badly — fillets, posts, manholes.
reseauxNoPlumbing pipe runs (EF/EC/EU/EV/EP/chauffage) — used only by cao_pdf (technical plan + linear-meter quantities per type).
toituresNoRoofs — used only by cao_pdf. WITHOUT this field: a flat roof is auto-generated over the footprint of ALL walls (legacy default). WITH it: compose freely — each entry can target a subset of walls (via `murs`), letting you build an L-shaped building's roof, or add a dormer on top of a main roof.
plomberieNoSanitary fixtures (sink, WC, shower…) — used only by cao_pdf. Same positioning as electricite.
decorationNoPaint/finish per wall — used only by cao_pdf. Colors the elevations (exterior face) and the axonometric view (face auto-detected by orientation relative to the building's centroid).
ouverturesNoDoors/windows embedded in a wall — used only by cao_pdf (elevations + axonometric view), no effect on dxf/metres.
electriciteNoElectrical symbols (outlets, switches, lights…) — used only by cao_pdf (dedicated technical plan + quantities), no effect on dxf/metres/render. Position: attached to a wall (`mur`+`position`, like ouvertures) or free (`x`,`y`).
compositionsNoNamed wall/slab layer sets declared by the project. A key that matches an inferred kind (mur_exterieur, refend, cloison, plancher, toiture) or murs[].composition drops the Hypothese flag. Each value is {libelle, couches: [{cle, epaisseur?}]}. cle: enduit, bloc_beton, isolant, ba13, ossature, enduit_platre, beton_arme, tuile, charpente, etancheite. Omit epaisseur on the load-bearing layer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / murs / items / properties / existant
      Added value: +{
+  "description": "Optional: true for a wall of the EXISTING building when the scene is an extension. cao_permis then counts as created only what the works add.",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / plomberie / items / properties / type / enum
      Previous value: -[
-  "baignoire",
-  "chauffe_eau",
-  "compteur_eau",
-  "douche",
-  "evier",
-  "lavabo",
-  "radiateur",
-  "wc"
-]New value: +[
+  "baignoire",
+  "chauffe_eau",
+  "compteur_eau",
+  "douche",
+  "evier",
+  "lavabo",
+  "module_hydraulique",
+  "pac_exterieure",
+  "radiateur",
+  "wc"
+]
  3. Added

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and meets it: it discloses what gets checked, that results are returned per specification with applicable and failing elements and reasons, that `bcf: true` produces BCF 2.1 topics, and that omitting `ids` switches to the built-in French housing IDS. This is rich, actionable behavioral detail.

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

Conciseness3/5

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

The description is a single dense run-on sentence with heavy parentheses and semicolons. It contains useful detail, but the structure makes it harder to scan than necessary; bullet points or shorter sentences would improve readability without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 15 nested parameters and no output schema, the description explains the core behavior, inputs (scene vs IFC), default mode, and return shape. It leaves handling of the many scene-building parameters to the schema, which is already fully annotated, so only a slightly more explicit note about the role of those parameters keeps it from a 5.

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 is 3; the description adds extra meaning beyond the schema for `bcf` (failures become BCF topics with objects) and `ids` (default French housing IDS and its scope), and frames `ifc` as the architect's model path. That pushes it above baseline.

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 opens with a concrete trigger ('WHEN a BIM manager's information requirements ... must be checked') and names the exact resource: an IDS 1.0 file checked against the scene's model or an architect's IFC. It enumerates the checks (entity, attribute, property, classification, material, partOf, required/optional/prohibited, target IFC version), making the tool's function unmistakable and easily told apart from generic cao_verifier or cao_valider_ifc.

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

Usage Guidelines4/5

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

It states when to use the tool (before delivery, on a BIM model) and gives two distinct input routes (scene-built model vs architect's IFC) plus the fallback IDS when `ids` is omitted. It does not explicitly name sibling tools to exclude, so the guidance stops short of a 5.

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

All immobilier toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources