Skip to main content
Glama

DVF Scraper France: Real Estate Comps, Comparable Sales, Prices

get_france_property_sales
Read-only

Fetch official DVF French property sales by city or postal code for price, €/m², surface, rooms, date, energy class and median price summaries.

Instructions

Real property sales in France (official DVF data) for a city or postal code: price paid, price per m2, surface, rooms, date, with the energy class of the home when known and a median price summary. Pay per result on your Apify account: run start $0.003, property sale $0.0005.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_france_property_sales"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearsNoSale years to load, between 2021 and 2026 (2021 = July to December, 2026 = January to June: the State's October 2026 release covers July 2021 to June 2026; DVF is published with a few months of delay, in April and October).
locationsNoFrench cities, postal codes or INSEE codes: "Grenoble", "Paris", "38000", "33063"… Paris, Lyon and Marseille automatically cover all their arrondissements.
maxSurfaceNoKeep sales up to this living surface.
minSurfaceNoKeep sales with at least this living surface.
propertyTypesNohouse, apartment, commercial, land, outbuilding.
includeRentalYieldNoFor each sale: the State's asking-rent indicator of the commune for a typical home of that kind (Carte des loyers, charges included), and the gross yield it implies at the real sale price. The free summary gives median yields per city and ranks communes or arrondissements. Free, no extra time.
includeEnergyRatingNoMatches each sale to its official energy performance certificate (ADEME open data): energy class A-G, CO2 class, kWh/m²/year and certificate date. Free. A class is only attached when the address, property type, surface and date agree; about one sale in two gets one.
maxSalesPerLocationNoMost recent first. Summary statistics still use ALL matching sales. Default here: 50.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.3
    • changedInput schema / properties / years / description
      Previous value: -"Sale years to load, between 2021 and 2025 (the State publishes DVF data with a few months of delay, in April and October)."New value: +"Sale years to load, between 2021 and 2026 (2021 = July to December, 2026 = January to June: the State's October 2026 release covers July 2021 to June 2026; DVF is published with a few months of delay, in April and October)."
  2. First observedv0.1.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: an explicit pay-per-result cost model ($0.003 per run start, $0.0005 per property sale), which materially affects how an agent should size a query. It stops short of mentioning latency, pagination, or failure modes.

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?

Two sentences, both front-loaded: the first states the resource, scope, and returned fields; the second states cost. No filler, no repetition of the title.

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 must explain returns, and it does: price paid, price per m2, surface, rooms, date, energy class, and a median summary. Combined with the pricing model and the schema's own coverage of data-release timing, an agent has what it needs to call this correctly.

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%, with detailed per-parameter notes on year ranges, location formats, and how maxSalesPerLocation does not affect summary statistics, so the schema carries the semantics. The description adds no parameter-level meaning of its own, only output-level information, so the baseline 3 applies.

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?

Names a specific resource and verb: real property sales in France from official DVF data, scoped to a city or postal code. It also enumerates the returned fields (price paid, price per m2, surface, rooms, date, energy class, median summary), which separates it cleanly from siblings like get_france_energy_ratings or get_france_building_permits.

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

Usage Guidelines3/5

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

Usage is implied by the phrasing 'for a city or postal code' and the 'comps' framing in the title, so an agent can infer this is the comparable-sales tool. However, it never states when to prefer it over related siblings (e.g. energy ratings or building permits), nor any exclusions or prerequisites.

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