Skip to main content
Glama

france-data-mcp

by io.github.cturkieh

reconcilier_finess_sirene

Read-onlyIdempotent

Croise FINESS DREES ↔ SIRENE INSEE V3.11 et calcule un score de cohérence (Sørensen-Dice sur bigrammes) pour chaque SIRET candidat. Utile pour confirmer/infirmer un appariement num_finess ↔ SIRET avant prospection ou cross-check qualité.

Logique :

  1. Récupère FINESS (raison sociale + adresse libellée)

  2. Récupère SIRET candidats via la table RPPS

  3. Pour chaque SIRET, lookup SIRENE puis calcule 3 sous-scores :

    • nom : Dice sur raison sociale (FINESS vs SIRENE.uniteLegale)

    • adresse : Dice sur adresse complète

    • telephone : binaire 0/1 (toujours 0 actuellement : SIRENE n'expose pas le tel)

  4. Score global = pondération (nom 0.5, adresse 0.4, tel 0.1)

  5. Verdict brut : match (≥0.8) / partial (0.5..0.8) / mismatch (<0.5)

Algorithme PUBLIC (Sørensen-Dice est dans la littérature depuis 1948). Aucune valeur ajoutée Unilabs ici — c'est une primitive ouverte. La connaissance propriétaire (mapping enseignes ↔ SELAS) reste côté Geo Intel.

Format : objet LookupResult. Quand found: true, retourne { num_finess, candidates, skipped } :

  • candidates : tableau trié par score_global décroissant (meilleur match en premier)

  • skipped : SIRET candidats qu'on n'a PAS pu réconcilier (lookup SIRENE rejected ou not_found) avec la reason. Permet au caller de distinguer 'aucun SIRET candidat trouvé' (found: false LookupResult.not_found) de 'N SIRETs candidats mais tous rejetés par SIRENE' (candidates: [] + skipped: [...]).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
num_finessYesNuméro FINESS exact (9 chiffres).

Output Schema

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

TDQS

A4.4/5.0
Behavior5/5

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

The description extensively details behavioral traits: algorithm (Sørensen-Dice on bigrams), score computation, verdict thresholds, and output format including the `skipped` field. Annotations already indicate read-only, open-world, idempotent, non-destructive; the description adds value with the internal logic and edge cases.

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 well-structured with clear sections and bullet points, making it easy to read. It is slightly lengthy (four paragraphs) but each part serves a purpose. Some algorithmic details could be condensed, but overall it is efficient.

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 and the presence of an output schema, the description provides a complete picture: input, algorithm, output format (including handling of null cases like 'not_found' vs empty candidates). Nothing essential is missing.

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?

The single parameter 'num_finess' is fully described in the schema (9-digit string). The description adds context about how it is used to fetch FINESS data, but does not provide additional semantic constraints beyond the schema. With 100% schema coverage, a score of 3 is appropriate.

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: cross-referencing FINESS and SIRENE data and computing a coherence score for FINESS-SIRET matching. It uses specific verbs ('Croise', 'calcule') and identifies the resource (FINESS, SIRENE). The tool is distinct from siblings, none of which perform this reconciliation.

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 explicitly says the tool is useful 'pour confirmer/infirmer un appariement num_finess ↔ SIRET avant prospection ou cross-check qualité', providing clear context. It does not, however, mention when not to use it or suggest alternative tools, but the specificity is sufficient.

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