Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_get_college_ips

Retrieve Indice de Position Sociale (IPS) for middle schools in La Réunion. Filter by commune, sector, and school year to assess social mix and educational inequality.

Instructions

DEPP Indice de Position Sociale (IPS) of middle schools (collèges) in La Réunion. IPS is a 50-200 score that summarizes the average socio-professional category of pupils' parents (higher = more privileged students). It is the standard tool to assess school social mix and educational inequality. Returns school name, UAI ID, commune, sector (Public/Privé sous contrat), school year, IPS value, IPS standard deviation. Sorted IPS descending.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
communeNoCommune name prefix match
sectorNoSchool sector: "Public" (public) or "Privé sous contrat" (subsidized private)
rentreeNoSchool year (rentrée), format YYYY-YYYY. Examples: "2021-2022", "2022-2023"
limitNoMax schools to return (1-500, default 100)

Implementation Reference

  • Registration of the 'reunion_get_college_ips' tool via server.tool() on the McpServer. The tool name and description are defined here.
    export function registerEducationTools(server: McpServer): void {
      server.tool(
        'reunion_get_college_ips',
        'DEPP Indice de Position Sociale (IPS) of middle schools (collèges) in La Réunion. IPS is a 50-200 score that summarizes the average socio-professional category of pupils\' parents (higher = more privileged students). It is the standard tool to assess school social mix and educational inequality. Returns school name, UAI ID, commune, sector (Public/Privé sous contrat), school year, IPS value, IPS standard deviation. Sorted IPS descending.',
        {
          commune: z.string().optional().describe('Commune name prefix match'),
          sector: z.enum(['Public', 'Privé sous contrat']).optional().describe('School sector: "Public" (public) or "Privé sous contrat" (subsidized private)'),
          rentree: z.string().optional().describe('School year (rentrée), format YYYY-YYYY. Examples: "2021-2022", "2022-2023"'),
          limit: z.number().int().min(1).max(500).default(100).describe('Max schools to return (1-500, default 100)'),
        },
        async ({ commune, sector, rentree, limit }) => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_IPS_COLLEGES, {
              where: buildWhere([
                commune ? `nom_de_la_commune LIKE ${quote(`${commune}%`)}` : undefined,
                sector ? `secteur = ${quote(sector)}` : undefined,
                rentree ? `rentree_scolaire = ${quote(rentree)}` : undefined,
              ]),
              order_by: 'ips DESC',
              limit,
            });
            return jsonResult({
              total_schools: data.total_count,
              schools: data.results.map((row) => ({
                school: pickString(row, ['nom_de_l_etablissment']),
                uai: pickString(row, ['uai']),
                commune: pickString(row, ['nom_de_la_commune']),
                sector: pickString(row, ['secteur']),
                rentree: pickString(row, ['rentree_scolaire']),
                ips: pickNumber(row, ['ips']),
                ips_stddev: pickNumber(row, ['ecart_type_de_l_ips']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to fetch college IPS');
          }
        }
      );
  • Handler function for the 'reunion_get_college_ips' tool. Queries the 'indices-de-position-sociale-dans-les-colleges-a-la-reunion' dataset via the client, filters by optional commune/sector/rentree parameters, orders by IPS descending, and returns school info (name, UAI, commune, sector, rentree, IPS, IPS stddev).
    export function registerEducationTools(server: McpServer): void {
      server.tool(
        'reunion_get_college_ips',
        'DEPP Indice de Position Sociale (IPS) of middle schools (collèges) in La Réunion. IPS is a 50-200 score that summarizes the average socio-professional category of pupils\' parents (higher = more privileged students). It is the standard tool to assess school social mix and educational inequality. Returns school name, UAI ID, commune, sector (Public/Privé sous contrat), school year, IPS value, IPS standard deviation. Sorted IPS descending.',
        {
          commune: z.string().optional().describe('Commune name prefix match'),
          sector: z.enum(['Public', 'Privé sous contrat']).optional().describe('School sector: "Public" (public) or "Privé sous contrat" (subsidized private)'),
          rentree: z.string().optional().describe('School year (rentrée), format YYYY-YYYY. Examples: "2021-2022", "2022-2023"'),
          limit: z.number().int().min(1).max(500).default(100).describe('Max schools to return (1-500, default 100)'),
        },
        async ({ commune, sector, rentree, limit }) => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_IPS_COLLEGES, {
              where: buildWhere([
                commune ? `nom_de_la_commune LIKE ${quote(`${commune}%`)}` : undefined,
                sector ? `secteur = ${quote(sector)}` : undefined,
                rentree ? `rentree_scolaire = ${quote(rentree)}` : undefined,
              ]),
              order_by: 'ips DESC',
              limit,
            });
            return jsonResult({
              total_schools: data.total_count,
              schools: data.results.map((row) => ({
                school: pickString(row, ['nom_de_l_etablissment']),
                uai: pickString(row, ['uai']),
                commune: pickString(row, ['nom_de_la_commune']),
                sector: pickString(row, ['secteur']),
                rentree: pickString(row, ['rentree_scolaire']),
                ips: pickNumber(row, ['ips']),
                ips_stddev: pickNumber(row, ['ecart_type_de_l_ips']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to fetch college IPS');
          }
        }
      );
  • Input schema for the tool using Zod: commune (optional string), sector (optional enum 'Public'/'Privé sous contrat'), rentree (optional string), limit (int 1-500, default 100).
    {
      commune: z.string().optional().describe('Commune name prefix match'),
      sector: z.enum(['Public', 'Privé sous contrat']).optional().describe('School sector: "Public" (public) or "Privé sous contrat" (subsidized private)'),
      rentree: z.string().optional().describe('School year (rentrée), format YYYY-YYYY. Examples: "2021-2022", "2022-2023"'),
      limit: z.number().int().min(1).max(500).default(100).describe('Max schools to return (1-500, default 100)'),
    },
  • Dataset constant DATASET_IPS_COLLEGES = 'indices-de-position-sociale-dans-les-colleges-a-la-reunion' used by the handler to query the correct data source.
    const DATASET_IPS_COLLEGES = 'indices-de-position-sociale-dans-les-colleges-a-la-reunion';
  • Import of registerEducationTools from education.ts into the central module registration file.
    import { registerEducationTools } from './education.js';
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the score range, meaning, sort order (IPS descending), and returned fields. It does not mention data freshness, pagination, or authentication needs, but for a simple data retrieval tool, the disclosed behaviors are sufficient.

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 concise with three sentences. The first sentence states the tool's purpose, the second explains IPS, and the third lists output fields and sort order. It is front-loaded and lacks any filler or redundancy.

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?

The description lists the output fields (school name, UAI ID, commune, sector, school year, IPS value, IPS standard deviation) and sort order, which is complete for a data retrieval tool without an output schema. It provides all necessary context for an agent to understand what will be returned.

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 has 100% description coverage for all 4 parameters, so the description does not need to add much. It adds overall context about IPS but does not elaborate on parameter semantics beyond what the schema already provides. The baseline of 3 is appropriate because the schema already documents the parameters adequately.

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 explicitly states it returns IPS scores for middle schools (collèges) in La Réunion, defines IPS as a 50-200 score, and lists the output fields. It clearly distinguishes from siblings like reunion_get_lycee_ips (high schools) by specifying 'collèges' and mentioning the return fields.

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 provides context on what IPS is and when to use it (standard tool to assess school social mix and educational inequality), but does not explicitly state when not to use this tool or mention alternative tools. However, the context implies use for middle school IPS only, and siblings like reunion_get_lycee_ips are separate.

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