Skip to main content
Glama
cturkieh

France Data MCP

compare_adresse_cnam_vs_finess

Read-onlyIdempotent

Compare health center addresses across CNAM and FINESS DREES to detect unsynchronized address updates. Returns both addresses, dice score, and match status.

Instructions

Compare l'adresse d'un centre de santé côté CNAM (Annuaire santé Ameli) vs FINESS DREES pour un même num_finess. Primitive brute SANS interprétation métier — retourne les deux adresses, un score_dice (0..1, informatif ; null si non comparable car finess_absent) et un statut. Le caller décide quoi faire de la divergence.

Utilité : signaler un déménagement propagé par une source mais pas (encore) par l'autre (ex: CNAM '5 RUE DE L'ARQUEBUSE AUTUN' vs FINESS '15 BD BERNARD GIBERSTEIN AUTUN' pour le même FINESS). Équivalent côté centre de santé de compare_raison_sociale_finess_vs_rpps.

Statut (présent uniquement sur found: true) :

  • match : adresses strictement égales après normalisation

  • match_after_abbreviation_normalization : égales après expansion des abréviations de voie FR (R/RUE, BD/BOULEVARD, AV/AVENUE…) — MÊME adresse, simple abréviation DREES vs CNAM, PAS un déménagement

  • divergent_after_normalization : adresses réellement différentes (déménagement non synchronisé entre sources)

  • finess_absent : le CDS existe côté CNAM mais le num_finess est absent de FINESS DREES (latence sync bimensuelle)

Format : objet LookupResult discriminé par found. Si le num_finess n'est PAS un centre de santé CNAM, le tool retourne {found: false, lookupStatus: 'not_found', message} (utiliser etablissement_by_finess pour un établissement non-CDS).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
num_finessYesNuméro FINESS exact (9 chiffres).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
foundYes
lookupStatusYes
keyNoClé recherchée (SIREN, num_finess, code INSEE, …).
messageNoExplication actionnable quand `found=false` (cause probable + remédiation).
Behavior5/5

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

Discloses all behavioral traits: returns discriminated object, explains each possible status (match, match_after_abbreviation_normalization, divergent_after_normalization, finess_absent), explains score_dice. No contradictions with annotations (readOnlyHint, 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?

Well-structured, front-loaded with purpose. Some verbosity in status enumeration, but overall efficient. Could be slightly more concise without losing clarity.

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?

Covers purpose, return format, status meanings, edge cases (finess_absent, not found). Output schema exists. Sibling tool mentioned. Complete for a comparison tool of this complexity.

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?

Schema coverage 100% with one parameter described. Description adds context: explains valid use (only for center de santé) and what happens if not, thus adding value beyond schema.

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?

Clearly states the verb 'compare' and the resources (address of health center from CNAM vs FINESS). Explicitly distinguishes from sibling tool 'compare_raison_sociale_finess_vs_rpps' by calling it equivalent for centers.

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?

States it is a raw primitive with no interpretation, leaving decision to caller. Provides explicit when-not: use 'etablissement_by_finess' for non-CDS establishments. Also explains what happens when the finess does not correspond to a health center.

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