Skip to main content
Glama

france-data-mcp

by io.github.cturkieh

panorama_implantation_complet

Read-onlyIdempotent

Étude d'implantation labo en 1 appel (V0.23). Géocode l'adresse cible puis agrège EN PARALLÈLE 7 sections : territoire (densités PS commune vs national + établissements), demande (profil démographique du BASSIN — rayon — via profil_iris : âge, CSP, revenu pondéré), concurrents (labos FINESS), pourvoyeurs (MCO/EHPAD/SSR/dialyse — drivers écosystémiques), prescripteurs (médecins RPPS + IDEL Ameli), cds (centres de santé), referentiels (qualité couverture FINESS↔SIRENE).

Remplace ~15 appels MCP individuels par 1. Renvoie des RÉSUMÉS (count / top-N / moyenne), JAMAIS de listes brutes. AUCUNE interprétation métier (pas de 'désert médical' ni de verdict GO/NO-GO) — le caller LLM applique sa grille.

DÉGRADATION (lis couverture — 1 drapeau par section) : "ok" | "partiel:<raison>" | "indisponible:<raison>". Si une source est down, SA section est flaggée et le RESTE est renvoyé — comble alors le trou via l'outil unitaire correspondant (etablissements_finess_in_radius, professionnels_rpps_in_radius, densite_sante, centres_sante_in_radius…). Échec d'ANCRAGE (géocodage KO / adresse douteuse / code INSEE indérivable) = rejet total (RangeError).

Pièges internalisés : Paris/Lyon/Marseille basculés sur le département (meta.plm_mode=true) ; prescripteurs expose precis_count (PS géolocalisés à l'adresse, pas au centroïde commune) ; cds sans distance individuelle (centroïde commune).

WORKFLOW : appelle CET outil pour DÉMARRER une étude, puis creuse les sections partiel/indisponible via les unitaires, puis enrichir_concurrents sur le top 3 de concurrents.top.

Sources : IGN (géocodage), FINESS DREES, RPPS/ANS, Ameli/CNAM, INSEE/FILOSOFI, SIRENE/DINUM.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pointNoCoordonnées { lat, lon } si déjà connues (skip géocodage). Fournir `code_insee` avec.
adresseNoAdresse cible, géocodée en interne via IGN. Ex: "12 rue Nationale, Lille". XOR avec `point`.
rayon_kmNoRayon du bassin de l'étude (km). Défaut 5.
code_inseeNoCode INSEE commune (avec `point`, quand le géocodage est déjà fait).

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already indicate readOnly, openWorld, idempotent, non-destructive. Description adds parallel aggregation, degradation flags ('ok', 'partiel', 'indisponible'), internalized pitfalls (PLM mode for big cities, precise count for prescripteurs), and source references. No contradiction with annotations.

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 dense and well-structured with section list and workflow steps. Minor redundancy (e.g., 'Renvoie des RÉSUMÉS...' restates, but key info). Front-loaded with purpose.

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?

Despite no output schema, the description fully covers return values (summaries, degradation flags), edge cases (partial failure, anchorage failure), and internal logic (parallel execution, pitfalls). Sufficient for an agent to use 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?

All 4 parameters have descriptions in schema (100% coverage). Description adds critical context: XOR relationship between point and adresse, code_insee with point, default rayon_km=5, and behavior when point is used (skip geocoding).

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 it's an 'étude d'implantation labo' that aggregates 7 sections in parallel, replacing 15 individual MCP calls. It lists each section and explicitly distinguishes from sibling tools by being the orchestration entry point.

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?

Explicit workflow: call this tool to start, then handle partial/indisponible sections with unitary tools, then enrich top 3 concurrents. Also specifies when total failure occurs (anchorage failure) and that it returns summaries, not raw lists, and no business interpretation.

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