Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_list_childcare_facilities

List early-childhood care facilities in Saint-Denis or La Possession, including crèches, micro-crèches, and haltes-garderies. Returns name, type, capacity, address, manager, and care mode.

Instructions

List early-childhood care facilities (Etablissements d'Accueil du Jeune Enfant, EAJE) in Saint-Denis or La Possession — currently the only two communes publishing this dataset. Covers crèches collectives, multi-accueil, micro-crèches, haltes-garderies. Returns name, type, category, capacity, address, manager, and (for La Possession) care mode, age range, opening hours, contact info. Useful for parents finding childcare, family-policy mapping.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
communeYesCommune name. Only "Saint-Denis" and "La Possession" publish this dataset
limitNoMax facilities to return (1-200, default 50)

Implementation Reference

  • Handler function for reunion_list_childcare_facilities tool. Takes 'commune' (Saint-Denis or La Possession) and 'limit' params. For Saint-Denis, fetches from DATASET_CHILDCARE_SAINT_DENIS and returns name, type, category, capacity, state, address, manager. For La Possession, fetches from DATASET_CHILDCARE_POSSESSION and returns name, type, care_mode, capacity, age_range, address, hours, phone, email, website, manager.
    server.tool(
      'reunion_list_childcare_facilities',
      'List early-childhood care facilities (Etablissements d\'Accueil du Jeune Enfant, EAJE) in Saint-Denis or La Possession — currently the only two communes publishing this dataset. Covers crèches collectives, multi-accueil, micro-crèches, haltes-garderies. Returns name, type, category, capacity, address, manager, and (for La Possession) care mode, age range, opening hours, contact info. Useful for parents finding childcare, family-policy mapping.',
      {
        commune: z.enum(['Saint-Denis', 'La Possession']).describe('Commune name. Only "Saint-Denis" and "La Possession" publish this dataset'),
        limit: z.number().int().min(1).max(200).default(50).describe('Max facilities to return (1-200, default 50)'),
      },
      async ({ commune, limit }) => {
        try {
          if (commune === 'Saint-Denis') {
            const data = await client.getRecords<RecordObject>(DATASET_CHILDCARE_SAINT_DENIS, { limit });
            return jsonResult({
              commune,
              total_facilities: data.total_count,
              facilities: data.results.map((row) => ({
                name: pickString(row, ['nom']),
                type: pickString(row, ['type']),
                category: pickString(row, ['categorie']),
                capacity: pickNumber(row, ['capacite']),
                state: pickString(row, ['etat']),
                address: pickString(row, ['adresse']),
                manager: pickString(row, ['gestionnai']),
              })),
            });
          }
          const data = await client.getRecords<RecordObject>(DATASET_CHILDCARE_POSSESSION, { limit });
          return jsonResult({
            commune,
            total_facilities: data.total_count,
            facilities: data.results.map((row) => ({
              name: pickString(row, ['nom_de_l_etablissement']),
              type: pickString(row, ['type_d_etablissement']),
              care_mode: pickString(row, ['mode_d_accueil']),
              capacity: pickNumber(row, ['capacite_d_accueil_et_agrement']),
              age_range: pickString(row, ['tranche_d_age']),
              address: pickString(row, ['adresse']),
              hours: pickString(row, ['horaires_et_jours_de_d_ouverture']),
              phone: pickString(row, ['telephone']),
              email: pickString(row, ['e_mail']),
              website: pickString(row, ['site_web']),
              manager: pickString(row, ['gestionnaire']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to list childcare facilities');
        }
      }
    );
  • Schema definition: commune (enum of Saint-Denis or La Possession) and limit (1-200, default 50).
    {
      commune: z.enum(['Saint-Denis', 'La Possession']).describe('Commune name. Only "Saint-Denis" and "La Possession" publish this dataset'),
      limit: z.number().int().min(1).max(200).default(50).describe('Max facilities to return (1-200, default 50)'),
    },
  • The tool is registered via server.tool() inside the registerSocialTools() function exported from social.ts.
    export function registerSocialTools(server: McpServer): void {
      server.tool(
        'reunion_get_caf_beneficiaries',
        'Monthly counts of beneficiaries of CAF (Caisse d\'Allocations Familiales) social benefits in La Réunion. Each row is one (month × benefit type). Covers RSA (revenu de solidarité active), AAH (allocation aux adultes handicapés), prestations familiales (allocations familiales, ASF, complément familial), prestations logement (APL, ALS, ALF), prime d\'activité, etc. Returns date, benefit type, beneficiary count. Sorted by date descending. Combine with reunion_get_caf_amounts for total euros paid.',
        {
          benefit_type: z.string().optional().describe('Benefit type label prefix match. Examples: "RSA", "AAH", "Prime d\'activité", "Allocations familiales", "APL"'),
          from: z.string().optional().describe('Inclusive lower bound on date, ISO format YYYY-MM-DD'),
          to: z.string().optional().describe('Inclusive upper bound on date, ISO format YYYY-MM-DD'),
          limit: z.number().int().min(1).max(500).default(50).describe('Max rows to return (1-500, default 50)'),
        },
        async ({ benefit_type, from, to, limit }) => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_CAF_BENEFICIARIES, {
              where: buildWhere([
                benefit_type ? `type_prestation LIKE ${quote(`${benefit_type}%`)}` : undefined,
                from ? `date >= date${quote(from)}` : undefined,
                to ? `date <= date${quote(to)}` : undefined,
              ]),
              order_by: 'date DESC',
              limit,
            });
            return jsonResult({
              total_rows: data.total_count,
              series: data.results.map((row) => ({
                date: pickString(row, ['date']),
                benefit_type: pickString(row, ['type_prestation']),
                beneficiaries: pickNumber(row, ['nbbeneficiaires']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to fetch CAF beneficiaries');
          }
        }
      );
    
      server.tool(
        'reunion_get_caf_amounts',
        'Monthly total amounts (in EUR) paid out by CAF Réunion for each social-benefit category. Each row is one (month × benefit type) with the cumulated payouts for that category. Useful for public-spending analysis, social-policy monitoring, comparison with beneficiary counts (use reunion_get_caf_beneficiaries to derive average per beneficiary). Sorted by date descending.',
        {
          benefit_type: z.string().optional().describe('Benefit type label prefix match. Examples: "RSA", "AAH", "Prime d\'activité", "Allocations familiales"'),
          from: z.string().optional().describe('Inclusive lower bound on date, ISO format YYYY-MM-DD'),
          to: z.string().optional().describe('Inclusive upper bound on date, ISO format YYYY-MM-DD'),
          limit: z.number().int().min(1).max(500).default(50).describe('Max rows to return (1-500, default 50)'),
        },
        async ({ benefit_type, from, to, limit }) => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_CAF_AMOUNTS, {
              where: buildWhere([
                benefit_type ? `type_de_prestation LIKE ${quote(`${benefit_type}%`)}` : undefined,
                from ? `date >= date${quote(from)}` : undefined,
                to ? `date <= date${quote(to)}` : undefined,
              ]),
              order_by: 'date DESC',
              limit,
            });
            return jsonResult({
              total_rows: data.total_count,
              series: data.results.map((row) => ({
                date: pickString(row, ['date']),
                benefit_type: pickString(row, ['type_de_prestation']),
                amount_eur: pickNumber(row, ['montant']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to fetch CAF amounts');
          }
        }
      );
    
      server.tool(
        'reunion_list_childcare_facilities',
        'List early-childhood care facilities (Etablissements d\'Accueil du Jeune Enfant, EAJE) in Saint-Denis or La Possession — currently the only two communes publishing this dataset. Covers crèches collectives, multi-accueil, micro-crèches, haltes-garderies. Returns name, type, category, capacity, address, manager, and (for La Possession) care mode, age range, opening hours, contact info. Useful for parents finding childcare, family-policy mapping.',
        {
          commune: z.enum(['Saint-Denis', 'La Possession']).describe('Commune name. Only "Saint-Denis" and "La Possession" publish this dataset'),
          limit: z.number().int().min(1).max(200).default(50).describe('Max facilities to return (1-200, default 50)'),
        },
        async ({ commune, limit }) => {
          try {
            if (commune === 'Saint-Denis') {
              const data = await client.getRecords<RecordObject>(DATASET_CHILDCARE_SAINT_DENIS, { limit });
              return jsonResult({
                commune,
                total_facilities: data.total_count,
                facilities: data.results.map((row) => ({
                  name: pickString(row, ['nom']),
                  type: pickString(row, ['type']),
                  category: pickString(row, ['categorie']),
                  capacity: pickNumber(row, ['capacite']),
                  state: pickString(row, ['etat']),
                  address: pickString(row, ['adresse']),
                  manager: pickString(row, ['gestionnai']),
                })),
              });
            }
            const data = await client.getRecords<RecordObject>(DATASET_CHILDCARE_POSSESSION, { limit });
            return jsonResult({
              commune,
              total_facilities: data.total_count,
              facilities: data.results.map((row) => ({
                name: pickString(row, ['nom_de_l_etablissement']),
                type: pickString(row, ['type_d_etablissement']),
                care_mode: pickString(row, ['mode_d_accueil']),
                capacity: pickNumber(row, ['capacite_d_accueil_et_agrement']),
                age_range: pickString(row, ['tranche_d_age']),
                address: pickString(row, ['adresse']),
                hours: pickString(row, ['horaires_et_jours_de_d_ouverture']),
                phone: pickString(row, ['telephone']),
                email: pickString(row, ['e_mail']),
                website: pickString(row, ['site_web']),
                manager: pickString(row, ['gestionnaire']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to list childcare facilities');
          }
        }
      );
  • registerSocialTools is imported from ./social.js in the modules index.
    import { registerSocialTools } from './social.js';
  • registerSocialTools(server) is called inside registerAllTools() to register all social tools including reunion_list_childcare_facilities.
    registerSocialTools(server);
Behavior4/5

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

No annotations provided, so description carries full burden. Discloses return fields, facility types, and data sources. Does not mention pagination details beyond limit, but overall behavior is well described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences: first defines core functionality and limitation, second details coverage and use cases. No superfluous information.

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

Completeness4/5

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

Covers purpose, scope, and output fields. No output schema, but description lists key fields. Could add pagination behavior, but limit parameter is in schema. Overall sufficient for a list tool.

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 covers both parameters with descriptions (100% coverage). Description adds context on why only two communes are available and what data is returned, 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?

Specifies verb 'list', resource 'early-childhood care facilities', geographic scope (two communes), types of facilities, and return fields. Clearly distinguishes from siblings like reunion_search_schools.

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?

States 'currently the only two communes publishing this dataset', giving clear context on applicability. Does not explicitly mention when not to use, but the constraint is clear enough for an AI agent.

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/Hug0x0/mcp-reunion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server