Skip to main content
Glama
cturkieh

France Data MCP

etablissements_finess_in_radius

Read-onlyIdempotent

Locate FINESS health establishments within a geographic radius. Filter by facility families such as MCO, SSR, EHPAD, or lab.

Instructions

Recherche d'établissements de santé FINESS dans un rayon géographique (PostGIS ST_DWithin). Filtrable par familles. 24 valeurs disponibles : mco, ssr, sld, had, psychiatrie, dialyse, ambulatoire, labo, imagerie, pharmacie, msp_cpts, ehpad, residence_autonomie, senior_accompagnement, ssiad, aide_domicile, handicap_enfants, handicap_adultes, addictologie, enfance_protection, pmi, hebergement_social, prevention_sante, groupement. Source : FINESS / DREES (dump CSV ingéré localement). Note : champ email toujours null (non exposé par FINESS public). Note : raison_sociale provient du dump DREES qui abrège les libellés longs (~38 car. max, ex 'CERBALLIANCE HA' pour 'CERBALLIANCE HAZEBROUCK'). Pour le nom légal complet, cross-check via SIREN/SIRET (entreprise_by_siren / etablissement_by_siret). Lentille : un filtre familles compte les établissements par leur catégorie FINESS principale. Les activités hébergées dans un site d'une autre catégorie (ex. plateau de biologie d'un hôpital sous famille=labo) ne sont pas comptées — voir le champ perimetre de la réponse. La famille imagerie renvoie le plus souvent 0 résultat (FINESS ne répertorie pas les cabinets d'imagerie).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lonYesLongitude du centre (WGS84).
latYesLatitude du centre (WGS84).
radius_kmNoRayon en km (0.1-50, défaut 5).
famillesNoFamilles FINESS à inclure (24 valeurs disponibles, voir enum). Si omis, toutes catégories.
limitNoNombre max de résultats (1-500, défaut 100).
include_freshnessNoSi true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant la dernière ingestion réussie par source (FINESS, Ameli, RPPS, CDS) avec `staleness_days`. Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNombre d'entrées retournées dans `results` (post-troncature).
totalNoEffectif réel avant troncature. Présent sur les tools de nomenclature paginés (lister_*) : `count` = échantillon, `total` = total réel, re-appeler avec un `limit` supérieur si `truncated`.
truncatedNotrue si le total réel dépasse `limit` (re-paginer via `offset` si supporté, ou augmenter `limit` sur les lister_*). Optional sur les tools de listing exhaustif (lister_*).
resultsYesEntrées métier (shape spécifique au tool, cf. description du tool).
query_metadataNoMetadata de la query (radius_km, departement, filtres appliqués, …).
freshnessNoFraîcheur des sources (présent si `include_freshness: true`).
perimetreNoLentille de la source : ce que le comptage inclut/exclut. Lire `completeness_note` et la restituer au lecteur final.
activite_hebergeeNoCompte juxtaposé des sites hébergeant l'activité correspondant à la famille filtrée, sous une autre catégorie FINESS. Distinct du `count` principal — lire `note` pour comprendre la sémantique et ne JAMAIS additionner les deux comptes sans préciser leur nature.
Behavior5/5

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

The description adds significant behavioral context beyond annotations: the filtering only counts primary categories, the 'imagerie' family often returns 0, the 'email' field is always null, and 'raison_sociale' is abbreviated. It also explains the 'include_freshness' parameter's effect. This fully discloses tool limitations and behavior, complementing the readOnlyHint annotation.

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 well-structured with purposeful sentences. It front-loads the core purpose, then lists parameters, behavior notes, and limitations. Every sentence earns its place without redundancy.

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 (6 parameters, 24 enum values, output schema exists), the description thoroughly covers all aspects: purpose, filtering, data source, field limitations, freshness option, and behavioral quirks. It provides complete guidance for an AI agent to select and invoke the tool correctly.

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

Parameters5/5

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

Although the input schema covers all 6 parameters with descriptions, the description adds crucial meaning: explaining the 24 enum values, the abbreviation in 'raison_sociale', the null email, the filtering behavior by primary category, and the 'include_freshness' effect. This goes beyond schema to guide usage effectively.

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's purpose: searching for FINESS health establishments within a geographic radius. It specifies the verb 'Recherche', the resource 'établissements de santé FINESS', and the context 'dans un rayon géographique'. This distinguishes it from siblings like 'etablissements_finess_by_categorie' which lacks geographic filtering.

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?

The description provides strong usage context, including family filtering with 24 listed values, data source notes, and caveats about null email and abbreviation of 'raison_sociale'. It implies when to use (geographic search) and provides alternative cross-check suggestions via SIREN/SIRET. However, it does not explicitly contrast with sibling tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cturkieh/france-data-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server