Skip to main content
Glama

Parcellaire — cadastre, DVF & DPE

by re.parcellai
OverviewDiscussionsAdmin

Détails d'une parcelle cadastrale

get_parcelle
Read-onlyIdempotent

Retourne la fiche de base d'une parcelle cadastrale à partir de son IDU (14 caractères) : surface, adresse, commune. Tout le reste est à demander via 'include', uniquement pour les sections utiles à la question (chaque section allonge la réponse) : parcelles adjacentes (parcelles_adjacentes : celles qui la touchent, avec surface, bâti et nombre de DPE ; pour toute question de voisinage ou quand l'adresse ou un DPE pointe une petite parcelle sans bâti), bâtiments (batiments), transactions immobilières (dvf), diagnostics énergétiques (dpes), zonage d'urbanisme (urbanisme, la plus lente), données bâtiment BDNB (bdnb), piscines, copropriétés (rnc), propriétaires personnes morales (majic_pm), permis de construire (sitadel). La réponse donne toujours le nombre d'éléments de chaque section (donnees_disponibles), même non demandée : s'en servir pour décider quelles sections lire.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
includeNoSections à inclure, ex: ['dvf', 'dpes']. Aucune par défaut : sans include, seule la fiche de base de la parcelle est retournée.
max_itemsNoNombre maximum d'éléments par section liste (défaut 30). Les sections tronquées sont signalées dans 'sections_tronquees'.
parcelle_idYesIDU de la parcelle, 14 caractères, ex: '33063000IK0001'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / include / anyOf
      Previous value: -[
-  {
-    "anyOf": [
-      {
-        "items": {
-          "enum": [
-            "batiments",
-            "dvf",
-            "dpes",
-            "urbanisme",
-            "bdnb",
-            "piscines",
-            "rnc",
-            "majic_pm",
-            "sitadel"
-          ],
-          "type": "string"
-        },
-        "type": "array"
-      },
-      {
-        "const": "",
-        "type": "string"
-      }
-    ]
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "items": {
+          "enum": [
+            "parcelles_adjacentes",
+            "batiments",
+            "dvf",
+            "dpes",
+            "urbanisme",
+            "bdnb",
+            "piscines",
+            "rnc",
+            "majic_pm",
+            "sitadel"
+          ],
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "const": "",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / include / description
      Previous value: -"Sections à inclure. Défaut: ['batiments', 'dvf', 'dpes']"New value: +"Sections à inclure, ex: ['dvf', 'dpes']. Aucune par défaut : sans include, seule la fiche de base de la parcelle est retournée."
  2. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed7 schema fields changed
    • addedInput schema / properties / include / anyOf
      Added value: +[
+  {
+    "anyOf": [
+      {
+        "items": {
+          "enum": [
+            "batiments",
+            "dvf",
+            "dpes",
+            "urbanisme",
+            "bdnb",
+            "piscines",
+            "rnc",
+            "majic_pm",
+            "sitadel"
+          ],
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "const": "",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / include / items
      Removed value: -{
-  "enum": [
-    "batiments",
-    "dvf",
-    "dpes",
-    "urbanisme",
-    "bdnb",
-    "piscines",
-    "rnc",
-    "majic_pm",
-    "sitadel"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / include / type
      Removed value: -"array"
    • addedInput schema / properties / max_items / anyOf
      Added value: +[
+  {
+    "anyOf": [
+      {
+        "maximum": 200,
+        "minimum": 1,
+        "type": "integer"
+      },
+      {
+        "const": "",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / max_items / maximum
      Removed value: -200
    • removedInput schema / properties / max_items / minimum
      Removed value: -1
    • removedInput schema / properties / max_items / type
      Removed value: -"integer"
  4. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare the safe read-only, idempotent, non-destructive profile, and the description adds genuinely new behaviour: every response carries per-section element counts (donnees_disponibles) even when a section is not requested, truncation is flagged via sections_tronquees, and urbanisme is called out as the slowest section. No safety or auth caveats are given, but the annotations cover that ground.

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?

Front-loads the core purpose and the IDU input before the include guidance, and every clause carries information. It is a single dense paragraph with a long parenthetical section list, which is slightly harder to scan than a bulleted structure would be.

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?

With no output schema, the description compensates by describing the base fiche contents and the always-present donnees_disponibles counts and sections_tronquees signal, so an agent can plan a two-step read (discover counts, then request sections). Input semantics, cost, and latency are all covered for this read tool.

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, but the description goes further by explaining the semantics of the include values (what parcelles_adjacentes returns, that urbanisme is the slowest) and the cost model of requesting sections. max_items is left to the schema, which already documents the default 30 and truncation flag.

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?

States a specific verb and resource ('Retourne la fiche de base d'une parcelle cadastrale à partir de son IDU') and enumerates the returned fields (surface, adresse, commune), so an agent knows exactly what it produces. It never names the close sibling get_parcelle_context, so the boundary between the two is left for the agent to infer.

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?

Gives explicit when-to-use guidance for the optional sections ('uniquement pour les sections utiles à la question', plus a concrete trigger for parcelles_adjacentes on neighbourhood questions or small unbuilt parcels) and warns that each section lengthens the response. It does not compare itself against alternatives such as find_parcelles_by_address or get_parcelle_context.

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

All Parcellaire — cadastre, DVF & DPE 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