immobilier

cao_visite_camera

WHEN the automatic visit is good but ONE view is wrong — the façade is cut off, the ridge is out of frame, you want to step into the next room — and rewriting a whole chemin by hand would be absurd. PILOT the camera with a SEQUENCE OF ACTIONS instead of coordinates: ['avancer x3', 'pivoter_gauche', 'monter', 'zoom_arriere']. Actions are named (avancer, reculer, gauche, droite, the four diagonals, monter, descendre, pivoter_gauche/droite, incliner_haut/bas, zoom_avant, zoom_arriere, vue_initiale, vue_ensemble, piece_suivante, piece_precedente) or given as the KEYBOARD SHORTCUT a human would press in the render studio ('ctrl+8' = forward, numeric keypad laid out as a compass rose). Same grammar both ways, so a view prepared here is reproduced exactly by hand. Start from depuis (any waypoint of a chemin from cao_visite_plan) or omit it for an overall view. POST THE SCENE TOO: it enables wall collision (a step that would end inside a partition is refused and explained, not silently applied) and the room landmarks. Returns {camera, etapes[] (state after EACH action, with the reason for refused steps), chemin[]} — feed chemin straight back to cao_visite_studio to render that exact viewpoint in 4K. Catalogue of actions and keys (free, no key): GET /api/v1/cao/visite/commandes. Requires API key. REST: POST /api/v1/cao/visite/camera.

Input Schema

TableJSON Schema

Name	Required	Description
`murs`	No	Walls: plan segments extruded vertically
`plan`	No	2D reference lines
`boites`	No	Boxes (furniture, volumes): center x,y + dims l,p,h (mm)
`depuis`	No	Starting viewpoint — same shape as a `chemin` waypoint. Omit for an overall view of the building.
`actions`	Yes	Ordered sequence. Each item is an action code ('avancer'), a keyboard shortcut ('ctrl+8'), a repeat form ('avancer x3'), or {code, repetitions}. 200 items max.
`cercles`	No
`reseaux`	No	Plumbing pipe runs (EF/EC/EU/EV/EP/chauffage) — used only by cao_pdf (technical plan + linear-meter quantities per type).
`reglages`	No	Step sizes. Defaults: 500 mm per move, 250 mm per altitude step, 15° per rotation, ×1.25 per zoom. `grand_pas: true` = the Shift key (×4).
`toitures`	No	Roofs — 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.
`plomberie`	No	Sanitary fixtures (sink, WC, shower…) — used only by cao_pdf. Same positioning as electricite.
`decoration`	No	Paint/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).
`ouvertures`	No	Doors/windows embedded in a wall — used only by cao_pdf (elevations + axonometric view), no effect on dxf/metres.
`electricite`	No	Electrical 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`).

TDQS

A4.9/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full burden. It discloses wall-collision behavior (refused steps are explained, not silently applied), the return structure including per-action states, the API key requirement, and the free catalog endpoint. This goes well beyond basic safety hints and sets clear expectations for the agent.

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?

The description is long but tightly packed with actionable information: the WHEN clause leads, then the action grammar, starting point, scene requirement, return shape, and auxiliary endpoints. Every sentence earns its place, and the use of caps for key instructions ('PILOT', 'POST THE SCENE TOO') aids scannability without becoming noise.

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?

Given the tool's complexity (13 parameters, no output schema, no annotations), the description is remarkably complete. It explains the return object ({camera, etapes[], chemin[]}), the data flow from cao_visite_plan into `depuis` and from `chemin` into cao_visite_studio, the wall-collision feature, the free command catalog, and the API-key requirement. Nothing essential is left mysterious.

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 description coverage is 92%, so baseline is 3. The description adds meaningful context for key parameters: it explains the `actions` format ('avancer x3', 'ctrl+8', {code, repetitions}), the `depuis` source (a waypoint from cao_visite_plan), and why scene parameters matter (enable wall collision and room landmarks). It does not enumerate every scene field, but the schema already does that.

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 clearly states the tool pilots the camera via a sequence of actions rather than coordinates, and it opens with a specific scenario (automatic visit good but ONE view wrong). It distinguishes itself from siblings by referencing cao_visite_plan for the starting waypoint and cao_visite_studio for rendering the returned chemin.

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 when-to-use guidance: 'WHEN the automatic visit is good but ONE view is wrong... and rewriting a whole `chemin` by hand would be absurd.' It also explains how to start (from a waypoint of cao_visite_plan) and when to omit `depuis` for an overall view, plus how to feed the result to cao_visite_studio. The description navigates alternatives without ambiguity.

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

All immobilier tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0

Disambiguation4/5

Most tools are clearly distinct by purpose (e.g., quittance_loyer vs relance_impaye, or relance_facture_client vs relance_impaye). A few pairs like bon_intervention and fiche_mission could cause confusion, but detailed descriptions help resolve ambiguity.

Naming Consistency3/5

Tool names mix French and English, and use inconsistent patterns: some are noun-based (annonce_location, quittance_loyer), some verb-based (decide_campagne, obtenir_cle_api), and the cao_* tools use a prefix convention. Still readable but not uniform.

Tool Count2/5

41 tools is excessive for most servers, even one covering real estate and CAD. While the breadth is justified by multiple subdomains, the sheer number makes the surface hard to navigate and suggests possible over-fragmentation.

Completeness4/5

The tool set covers a wide range: rental lifecycle (annonce, EDL, quittance, relance), owner reporting, artisan documents, fiscal synthesis, CAD generation and verification, outreach, and guides. Minor gaps exist (e.g., no direct tenant/property CRUD), but for a document-generation server it is quite complete.

Resources

Need Help?