Skip to main content
Glama

Parcellaire — cadastre, DVF & DPE

Trouver les parcelles d'une adresse

find_parcelles_by_address
Read-onlyIdempotent

Géocode une adresse postale française (Base Adresse Nationale) puis retourne la ou les parcelles cadastrales correspondantes avec leur IDU. L'IDU permet ensuite d'appeler get_parcelle. Donner l'adresse la plus complète possible (numéro, rue, commune ou code postal). Une localisation non précisée ou ambiguë demande une clarification, jamais le choix automatique d'une commune. Une adresse représentative différente sur la fiche parcellaire n'annule pas le lien BAN–cadastre.

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": {
      "address": "<address>"
    },
    "name": "find_parcelles_by_address"
  }
}

Input Schema

NameRequiredDescriptionDefault
addressYesAdresse postale, ex: '10 quai des Chartrons, Bordeaux'
includeNoSections de get_parcelle à joindre si l'adresse mène à une seule parcelle, ex: ['dpes', 'dvf', 'batiments', 'rnc'] : la fiche arrive dans 'fiche_parcelle' sans appel get_parcelle séparé. Ignoré si plusieurs parcelles. Les risques ne sont pas une section : get_parcelle_context avec risques=true.
max_itemsNoNombre maximum d'éléments par section de fiche_parcelle (défaut 30).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / include / description
      Previous value: -"Sections de get_parcelle à joindre si l'adresse mène à une seule parcelle, ex: ['dpes', 'dvf', 'batiments', 'rnc'] : la fiche arrive dans 'fiche_parcelle' sans appel get_parcelle séparé. Ignoré si plusieurs parcelles."New value: +"Sections de get_parcelle à joindre si l'adresse mène à une seule parcelle, ex: ['dpes', 'dvf', 'batiments', 'rnc'] : la fiche arrive dans 'fiche_parcelle' sans appel get_parcelle séparé. Ignoré si plusieurs parcelles. Les risques ne sont pas une section : get_parcelle_context avec risques=true."
  2. Changed1 schema field changed
    • changedInput schema / properties / include / anyOf
      Previous 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"
      -  }
      -]New value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "items": {
      +          "enum": [
      +            "parcelles_adjacentes",
      +            "batiments",
      +            "dvf",
      +            "dpes",
      +            "urbanisme",
      +            "bdnb",
      +            "piscines",
      +            "rnc",
      +            "majic_pm",
      +            "sitadel",
      +            "audits"
      +          ],
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  3. Changed2 schema fields changed
    • addedInput schema / properties / include
      Added value: +{
      +  "anyOf": [
      +    {
      +      "anyOf": [
      +        {
      +          "items": {
      +            "enum": [
      +              "parcelles_adjacentes",
      +              "batiments",
      +              "dvf",
      +              "dpes",
      +              "urbanisme",
      +              "bdnb",
      +              "piscines",
      +              "rnc",
      +              "majic_pm",
      +              "sitadel"
      +            ],
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        {
      +          "const": "",
      +          "type": "string"
      +        }
      +      ]
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Sections de get_parcelle à joindre si l'adresse mène à une seule parcelle, ex: ['dpes', 'dvf', 'batiments', 'rnc'] : la fiche arrive dans 'fiche_parcelle' sans appel get_parcelle séparé. Ignoré si plusieurs parcelles."
      +}
    • addedInput schema / properties / max_items
      Added value: +{
      +  "anyOf": [
      +    {
      +      "anyOf": [
      +        {
      +          "maximum": 200,
      +          "minimum": 1,
      +          "type": "integer"
      +        },
      +        {
      +          "const": "",
      +          "type": "string"
      +        }
      +      ]
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Nombre maximum d'éléments par section de fiche_parcelle (défaut 30)."
      +}
  4. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  5. First observed

TDQS

A4.1/5.0
Behavior4/5

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

The annotations already declare read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real behavior beyond that: geocoding is against BAN, ambiguous input must not be silently resolved, and a differing representative address on the parcel record does not break the BAN–cadastre link. Return shape is not described, but the include parameter schema carries that.

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?

The core purpose and the IDU chaining come first, followed by input advice and the ambiguity rule. It is dense but every sentence carries actionable content; the closing note on representative addresses is niche but prevents a real misread.

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 three-parameter, read-only lookup with no output schema, the description covers what the tool does, how to phrase the address, how to resolve ambiguity, and how to chain to get_parcelle. The only remaining gap is what the multi-parcel result looks like and how include is ignored when several parcels match, which is only implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents address, include and max_items in detail. The description adds only an address completeness hint (number, street, commune or postal code), which is already close to the schema's own example. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb chain and resource: geocode a French postal address against the Base Adresse Nationale, then return the matching cadastral parcels with their IDU. This clearly separates it from find_parcelles_by_criteria (search by criteria) and from get_parcelle (which is explicitly named as the downstream step keyed by IDU).

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 gives concrete input guidance ('give the most complete address possible: number, street, commune or postal code') and an explicit handling rule: an imprecise or ambiguous location must trigger a clarification, never an automatic commune choice. It also explains the follow-on path via IDU to get_parcelle. It stops short of naming alternative siblings such as find_parcelles_by_criteria for non-address lookups.

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