Skip to main content
Glama

Parcellaire — cadastre, DVF & DPE

Estimer le prix d'un bien immobilier

estimate_property_price
Read-onlyIdempotent

Estime le prix de vente d'une maison ou d'un appartement en France à partir des transactions DVF récentes et d'un modèle statistique national. Localisation par 'address' OU par 'lat' + 'lng' + 'code_insee'. Retourne un prix total, une fourchette, un prix au m² et des facteurs explicatifs.

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": {
      "type_bien": "<type_bien>",
      "surface_m2": "<surface_m2>"
    },
    "name": "estimate_property_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude, si pas d'adresse
lngNoLongitude, si pas d'adresse
addressNoAdresse du bien (option la plus simple)
type_bienYesType de bien : 'maison' ou 'appartement'
classe_dpeNoClasse DPE si connue (affine l'estimation)
code_inseeNoCode INSEE de la commune, si pas d'adresse
surface_m2YesSurface habitable en m² (annonce ou DPE du logement), ex: 85. Jamais l'emprise au sol d'un bâtiment.
terrain_m2NoSurface du terrain en m² (maisons)
source_surfaceNoOrigine de surface_m2 : 'annonce', 'dpe' (DPE de ce logement), 'utilisateur', 'dvf' (surface bâtie d'une vente passée, approximation) ou 'hypothese' (surface supposée). 'emprise_au_sol' (batiments, BDNB, même multipliée par les niveaux) est refusée : ce n'est pas une surface habitable.
annee_constructionNoAnnée de construction, ex: 1975 (affine l'estimation)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / source_surface
      Added value: +{
      +  "anyOf": [
      +    {
      +      "anyOf": [
      +        {
      +          "enum": [
      +            "annonce",
      +            "dpe",
      +            "utilisateur",
      +            "dvf",
      +            "hypothese",
      +            "emprise_au_sol"
      +          ],
      +          "type": "string"
      +        },
      +        {
      +          "const": "",
      +          "type": "string"
      +        }
      +      ]
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Origine de surface_m2 : 'annonce', 'dpe' (DPE de ce logement), 'utilisateur', 'dvf' (surface bâtie d'une vente passée, approximation) ou 'hypothese' (surface supposée). 'emprise_au_sol' (batiments, BDNB, même multipliée par les niveaux) est refusée : ce n'est pas une surface habitable."
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / surface_m2 / description
      Previous value: -"Surface habitable en m², nombre, ex: 85"New value: +"Surface habitable en m² (annonce ou DPE du logement), ex: 85. Jamais l'emprise au sol d'un bâtiment."
  3. Changed3 schema fields changed
    • addedInput schema / properties / annee_construction / description
      Added value: +"Année de construction, ex: 1975 (affine l'estimation)"
    • changedInput schema / properties / surface_m2 / description
      Previous value: -"Surface habitable en m²"New value: +"Surface habitable en m², nombre, ex: 85"
    • addedInput schema / properties / type_bien / description
      Added value: +"Type de bien : 'maison' ou 'appartement'"
  4. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  5. Changed19 schema fields changed
    • addedInput schema / properties / address / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "type": "string"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / address / type
      Removed value: -"string"
    • addedInput schema / properties / annee_construction / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "maximum": 9007199254740991,
      +        "minimum": -9007199254740991,
      +        "type": "integer"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / annee_construction / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / annee_construction / minimum
      Removed value: --9007199254740991
    • removedInput schema / properties / annee_construction / type
      Removed value: -"integer"
    • addedInput schema / properties / classe_dpe / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "enum": [
      +          "A",
      +          "B",
      +          "C",
      +          "D",
      +          "E",
      +          "F",
      +          "G"
      +        ],
      +        "type": "string"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / classe_dpe / enum
      Removed value: -[
      -  "A",
      -  "B",
      -  "C",
      -  "D",
      -  "E",
      -  "F",
      -  "G"
      -]
    • removedInput schema / properties / classe_dpe / type
      Removed value: -"string"
    • addedInput schema / properties / code_insee / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "maxLength": 5,
      +        "minLength": 5,
      +        "type": "string"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / code_insee / maxLength
      Removed value: -5
    • removedInput schema / properties / code_insee / minLength
      Removed value: -5
    • removedInput schema / properties / code_insee / type
      Removed value: -"string"
    • addedInput schema / properties / lat / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "type": "number"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / lat / type
      Removed value: -"number"
    • addedInput schema / properties / lng / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "type": "number"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / lng / type
      Removed value: -"number"
    • addedInput schema / properties / terrain_m2 / anyOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "type": "number"
      +      },
      +      {
      +        "const": "",
      +        "type": "string"
      +      }
      +    ]
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedInput schema / properties / terrain_m2 / type
      Removed value: -"number"
  6. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description usefully adds that the result is model-derived from DVF and includes a range and explanatory factors, signalling uncertainty. It does not discuss coverage limits, data freshness, or failure modes for areas without transactions.

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?

Three short sentences: what it does, how to locate, what it returns. Nothing is wasted and the core purpose is front-loaded.

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?

With 10 parameters and no output schema, the description compensates by naming the returned values (total price, range, price/m², factors). It omits that optional inputs like classe_dpe, terrain_m2 and annee_construction meaningfully refine the estimate and stays silent on reliability caveats, leaving minor gaps.

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 baseline is 3; the schema already documents every parameter including the address-vs-coordinates fallback and the source_surface semantics. The description adds no parameter detail beyond repeating the localisation alternative, so no credit 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?

States a specific verb and resource ('Estime le prix de vente d'une maison ou d'un appartement en France'), plus the method (transactions DVF récentes, modèle statistique national). This clearly distinguishes it from siblings such as search_ventes_dvf or get_commune_stats, which retrieve data rather than produce a valuation.

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?

Explicitly gives the two accepted localisation modes ('address' OU 'lat' + 'lng' + 'code_insee'), which is actionable usage guidance. It does not, however, state when to prefer this tool over data-retrieval siblings or when an estimate should be avoided (e.g. insufficient DVF data).

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