Skip to main content
Glama
cturkieh

France Data MCP

densite_etablissements_sante

Read-onlyIdempotent

Calculate the density of healthcare establishments per 100,000 residents in a French department, filtered by facility type (e.g., hospitals, pharmacies). Optionally compare to the national average to identify under or over-equipped areas.

Instructions

Densité d'établissements de santé pour 100 000 habitants dans un département, par famille FINESS. Croise FINESS DREES (count) et INSEE Melodi (population municipale PMUN, recensement 2023).

Familles disponibles : labo (laboratoires de biologie médicale), pharmacie, ehpad, mco (court séjour médecine/chirurgie/obstétrique), ssr (soins de suite), psychiatrie, dialyse, imagerie, had (hospitalisation à domicile), msp_cpts (maisons de santé + CPTS), handicap_enfants, handicap_adultes, addictologie, pmi, prevention_sante, etc. Famille obligatoire — sans filtre, le ratio mélangerait labos / hôpitaux / EHPAD et n'aurait pas de sens.

compare_national: true ajoute la densité France entière (DOM inclus) + écart en %. Coût : 1 RPC count_finess + 1 appel Melodi (cacheable).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
code_deptYesCode INSEE du département (2-3 caractères, ex: '75', '13', '2A', '971').
familleYesFamille FINESS à compter (labo, pharmacie, ehpad, mco, ssr, psychiatrie, dialyse, imagerie, had, msp_cpts, handicap_enfants, handicap_adultes, addictologie, pmi, prevention_sante, etc.).
compare_nationalNoAjoute le calcul France entière + écart relatif en % (recommandé pour 'sous-doté'/'sur-doté').
Behavior4/5

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

Adds behavioral context beyond annotations: mentions data sources, cost of compare_national, and mandatory family filter. No contradiction with readOnlyHint. Could detail edge cases like missing data.

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 with bullet lists and explanations. Reasonably concise for complexity; slightly long but each sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks explicit description of output format (e.g., numbers per 100k, optional national comparison). Predictable but could be more complete for a statistical tool without output schema.

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?

Schema coverage 100%. Description adds extensive examples for famille, explains purpose and cost of compare_national, and reinforces mandatory nature of famille – all 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 tool computes density of health establishments per 100,000 inhabitants per department per FINESS family, using two data sources. Differentiates from sibling densite_professionnels_sante by focusing on establishments.

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?

Explicitly states famille is mandatory and explains why mixing families would be meaningless. Documents compare_national parameter and its cost. Lacks explicit when-not-to-use but context is clear.

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