Skip to main content
Glama

france-data-mcp

by io.github.cturkieh

rpps_dans_etablissement

Read-onlyIdempotent

Liste les PS rattachés à un établissement FINESS (num_finess 9 chiffres). Pivot RPPS↔FINESS — répond à "qui travaille dans ce labo / hôpital / clinique ?". Le mode_exercice distingue les libéraux exerçant sur place (vacations) des salariés. Couverture : RPPS expose ce lien quand le PS l'a déclaré ; salariés CH/CHU/cliniques bien couverts.

Sortie compacte : coords et distance_km sont null (le tool est par établissement, pas spatial — pour la géoloc, pivoter via etablissement_by_finess sur le num_finess). Catégorie par défaut : Civil (C, ~97 % — libéraux, salariés privés, hospitaliers contractuels). Opt-in : include_agents_publics: true ajoute Agents publics (M, ~0,3 % — PH titulaires, ARS, CNAM, Éducation nationale, PMI, militaires SSA) ; include_etudiants: true ajoute Étudiants (E, ~2,5 % — internes, externes, élèves IDE/SF). Réf : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/. Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
num_finessYes
include_etudiantsNo
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.
include_agents_publicsNo

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`.
resultsYesEntrées métier (shape spécifique au tool, cf. description du tool).
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.
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_*).
query_metadataNoMetadata de la query (radius_km, departement, filtres appliqués, …).
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.

TDQS

A4.8/5.0
Behavior5/5

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

The description adds significant behavioral context beyond annotations: it explains that coords and distance_km are null, the output is compact, the default category, opt-in behavior for agents publics and étudiants, and includes data source and license. No contradictions with annotations (readOnlyHint, idempotentHint, etc.).

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 description is front-loaded with the purpose and well-structured into sections (purpose, output, categories, opt-ins, references). It is longer than necessary but every sentence provides value. Could be slightly more concise, but overall efficient for the complexity.

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 parameter count (5), output schema existence, and many siblings, the description is extremely complete. It covers purpose, usage, parameter semantics, behavioral notes, data source, and references. It also complements the output schema by explaining what is null and why.

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?

The description adds meaning to parameters like include_agents_publics and include_etudiants with category percentages and examples, and explains num_finess format. However, the 'limit' parameter is not explicitly described in the description, though the schema provides basic type. Given low schema coverage (20%), the description compensates well but misses limit.

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 'Liste les PS rattachés à un établissement FINESS' with a specific verb and resource. It explains the tool's role as a pivot between RPPS and FINESS and explicitly differentiates from spatial tools by noting that coords are null, and suggests using 'etablissement_by_finess' for geolocation.

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

Usage Guidelines5/5

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

The description explicitly states when to use: to answer 'qui travaille dans ce labo / hôpital / clinique ?'. It provides explicit guidance on when not to use (for spatial queries) and names an alternative. It also explains opt-in parameters and default category, and discusses data coverage and limitations.

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

All france-data-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

While tools have distinct purposes, there is overlap among several similar tools (e.g., multiple professional and establishment search tools). The detailed descriptions help differentiate, but an agent may struggle to choose correctly among them.

Naming Consistency2/5

Naming mixes French and English, with no consistent pattern (e.g., 'enrichir_concurrents' vs 'inspect_site', 'etablissement_by_finess' vs 'etablissements_finess_in_radius'). This inconsistency makes the toolset harder to navigate.

Tool Count3/5

36 tools is high but justified given the broad domain. However, there are multiple tools for similar tasks (e.g., four professional search tools), suggesting some redundancy. The scope is borderline but acceptable.

Completeness4/5

The toolset covers a wide range of needs for French health data analysis: establishments, professionals, population, geocoding, demographics, and composite analyses. Few obvious gaps exist, though some specialized tasks might require additional integration.

Resources