Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_get_museum_attendance

Retrieve annual attendance figures for Musée de France in La Réunion, broken down by paid and free admissions, to support cultural policy evaluation and tourism analysis.

Instructions

Annual attendance figures for each Musée de France in La Réunion, broken down by paid vs free admissions. Returns year, museum name, Muséofile reference, city, paid visitors, free visitors, total visitors, notes, observations. Source: Ministère de la Culture / Patrimostat via data.regionreunion.com. Sorted by year descending. Useful for cultural-policy evaluation, tourism analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoYear filter (4 digits, e.g. 2022)
museumNoMuseum name prefix match (e.g. "Léon Dierx", "Stella Matutina")
limitNoMax rows to return (1-500, default 100)

Implementation Reference

  • The handler function for 'reunion_get_museum_attendance' tool. Fetches annual attendance figures for Musée de France in La Réunion from the 'frequentation-des-musees-de-franceculture' dataset, with optional filters for year and museum name, sorted by year descending.
    server.tool(
      'reunion_get_museum_attendance',
      'Annual attendance figures for each Musée de France in La Réunion, broken down by paid vs free admissions. Returns year, museum name, Muséofile reference, city, paid visitors, free visitors, total visitors, notes, observations. Source: Ministère de la Culture / Patrimostat via data.regionreunion.com. Sorted by year descending. Useful for cultural-policy evaluation, tourism analysis.',
      {
        year: z.number().int().optional().describe('Year filter (4 digits, e.g. 2022)'),
        museum: z.string().optional().describe('Museum name prefix match (e.g. "Léon Dierx", "Stella Matutina")'),
        limit: z.number().int().min(1).max(500).default(100).describe('Max rows to return (1-500, default 100)'),
      },
      async ({ year, museum, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_MUSEUM_ATTENDANCE, {
            where: buildWhere([
              year !== undefined ? `annee = ${year}` : undefined,
              museum ? `nom_du_musee LIKE ${quote(`${museum}%`)}` : undefined,
            ]),
            order_by: 'annee DESC',
            limit,
          });
          return jsonResult({
            total_rows: data.total_count,
            attendance: data.results.map((row) => ({
              year: pickNumber(row, ['annee']),
              museum: pickString(row, ['nom_du_musee']),
              museofile_ref: pickString(row, ['ref_musee']),
              city: pickString(row, ['ville']),
              paid_visitors: pickNumber(row, ['payant']),
              free_visitors: pickNumber(row, ['gratuit']),
              total_visitors: pickNumber(row, ['total']),
              note: pickString(row, ['note']),
              observations: pickString(row, ['observations']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to fetch museum attendance');
        }
      }
    );
  • Input schema for the tool: year (optional int), museum (optional string prefix), limit (int 1-500, default 100).
    {
      year: z.number().int().optional().describe('Year filter (4 digits, e.g. 2022)'),
      museum: z.string().optional().describe('Museum name prefix match (e.g. "Léon Dierx", "Stella Matutina")'),
      limit: z.number().int().min(1).max(500).default(100).describe('Max rows to return (1-500, default 100)'),
    },
  • Output schema: returns total_rows and an attendance array with year, museum, museofile_ref, city, paid_visitors, free_visitors, total_visitors, note, and observations.
      total_rows: data.total_count,
      attendance: data.results.map((row) => ({
        year: pickNumber(row, ['annee']),
        museum: pickString(row, ['nom_du_musee']),
        museofile_ref: pickString(row, ['ref_musee']),
        city: pickString(row, ['ville']),
        paid_visitors: pickNumber(row, ['payant']),
        free_visitors: pickNumber(row, ['gratuit']),
        total_visitors: pickNumber(row, ['total']),
        note: pickString(row, ['note']),
        observations: pickString(row, ['observations']),
      })),
    });
  • Registration of the tool via server.tool() call within registerCultureTools, which is called from src/modules/index.ts line 37.
    server.tool(
      'reunion_get_museum_attendance',
      'Annual attendance figures for each Musée de France in La Réunion, broken down by paid vs free admissions. Returns year, museum name, Muséofile reference, city, paid visitors, free visitors, total visitors, notes, observations. Source: Ministère de la Culture / Patrimostat via data.regionreunion.com. Sorted by year descending. Useful for cultural-policy evaluation, tourism analysis.',
      {
        year: z.number().int().optional().describe('Year filter (4 digits, e.g. 2022)'),
        museum: z.string().optional().describe('Museum name prefix match (e.g. "Léon Dierx", "Stella Matutina")'),
        limit: z.number().int().min(1).max(500).default(100).describe('Max rows to return (1-500, default 100)'),
      },
      async ({ year, museum, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_MUSEUM_ATTENDANCE, {
            where: buildWhere([
              year !== undefined ? `annee = ${year}` : undefined,
              museum ? `nom_du_musee LIKE ${quote(`${museum}%`)}` : undefined,
            ]),
            order_by: 'annee DESC',
            limit,
          });
          return jsonResult({
            total_rows: data.total_count,
            attendance: data.results.map((row) => ({
              year: pickNumber(row, ['annee']),
              museum: pickString(row, ['nom_du_musee']),
              museofile_ref: pickString(row, ['ref_musee']),
              city: pickString(row, ['ville']),
              paid_visitors: pickNumber(row, ['payant']),
              free_visitors: pickNumber(row, ['gratuit']),
              total_visitors: pickNumber(row, ['total']),
              note: pickString(row, ['note']),
              observations: pickString(row, ['observations']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to fetch museum attendance');
        }
      }
    );
  • Registration entry point: registerCultureTools(server) invoked from registerAllTools, which wires up all tools to the MCP server.
    registerCultureTools(server);
  • The dataset constant 'frequentation-des-musees-de-franceculture' used by the tool to query attendance data.
    const DATASET_MUSEUM_ATTENDANCE = 'frequentation-des-musees-de-franceculture';
Behavior3/5

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

No annotations are provided, so the description must convey behavioral traits. It notes that results are sorted by year descending, which is useful, but does not disclose other aspects like read-only nature, potential response size, or performance characteristics. It is adequate but not rich.

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?

The description is two sentences, front-loaded with the main purpose followed by details. Every sentence adds value, no redundancy, and it is efficiently structured.

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?

The description explains the return fields (year, museum name, reference, city, paid visitors, free visitors, total, notes, observations) and includes the data source. Without an output schema, this provides adequate context. Could mention typical row counts or handling of missing years, but the limit parameter is addressed.

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 input schema covers all three parameters with clear descriptions (100% coverage). The description adds that museum uses prefix matching and results are sorted by year descending, but these are minor additions. Baseline 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 it returns annual attendance figures for each Musée de France in La Réunion, broken down by paid vs free admissions. It lists specific fields and distinguishes itself from sibling tools that cover different data (e.g., tourism frequentation, air quality).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the tool is useful for cultural-policy evaluation and tourism analysis, but does not explicitly state when to use it versus alternatives like reunion_get_tourism_frequentation. No guidance on when not to use or prerequisites is provided.

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