Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_get_lycee_ips

Retrieve social position indices (IPS) for high schools in La Réunion by school year and pathway, including separate values for general/technological and vocational tracks.

Instructions

DEPP Indice de Position Sociale (IPS) for high schools (lycées) in La Réunion, by school year and pathway. Unlike colleges, lycées have separate IPS for the general/technological track (voie GT) and the vocational track (voie pro), plus a combined IPS. Returns school year, UAI, name, commune, sector, lycée type, three IPS values + standard deviations for GT and pro. Higher IPS = more privileged students.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
schoolNoSchool name prefix match
school_yearNoSchool year (rentrée), format YYYY-YYYY (e.g. "2022-2023")
communeNoCommune name prefix match
limitNoMax rows to return (1-200, default 50)

Implementation Reference

  • registerAllTools function calls registerEducationTools, which registers reunion_get_lycee_ips among other education tools
    export function registerAllTools(server: McpServer): void {
      registerAdministrationTools(server);
      registerCatalogTools(server);
      registerCommuneTools(server);
      registerCultureTools(server);
      registerEconomyTools(server);
      registerEducationTools(server);
  • Main implementation: server.tool('reunion_get_lycee_ips', ...) with Zod schema and async handler that queries the OpenDataSoft dataset 'indices-de-position-sociale-dans-les-lycees-a-la-reunion' and returns IPS data for lycées
    server.tool(
      'reunion_get_lycee_ips',
      'DEPP Indice de Position Sociale (IPS) for high schools (lycées) in La Réunion, by school year and pathway. Unlike colleges, lycées have separate IPS for the general/technological track (voie GT) and the vocational track (voie pro), plus a combined IPS. Returns school year, UAI, name, commune, sector, lycée type, three IPS values + standard deviations for GT and pro. Higher IPS = more privileged students.',
      {
        school: z.string().optional().describe('School name prefix match'),
        school_year: z.string().optional().describe('School year (rentrée), format YYYY-YYYY (e.g. "2022-2023")'),
        commune: z.string().optional().describe('Commune name prefix match'),
        limit: z.number().int().min(1).max(200).default(50).describe('Max rows to return (1-200, default 50)'),
      },
      async ({ school, school_year, commune, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_IPS_LYCEES, {
            where: buildWhere([
              school ? `nom_de_l_etablissment LIKE ${quote(`${school}%`)}` : undefined,
              school_year ? `rentree_scolaire = ${quote(school_year)}` : undefined,
              commune ? `nom_de_la_commune LIKE ${quote(`${commune}%`)}` : undefined,
            ]),
            limit,
          });
          return jsonResult({
            total_rows: data.total_count,
            schools: data.results.map((row) => ({
              school_year: pickString(row, ['rentree_scolaire']),
              uai: pickString(row, ['uai']),
              name: pickString(row, ['nom_de_l_etablissment']),
              commune: pickString(row, ['nom_de_la_commune']),
              sector: pickString(row, ['secteur']),
              lycee_type: pickString(row, ['type_de_lycee']),
              ips_general_technological: pickNumber(row, ['ips_voie_gt']),
              ips_vocational: pickNumber(row, ['ips_voie_pro']),
              ips_combined: pickNumber(row, ['ips_ensemble_gt_pro']),
              stddev_gt: pickNumber(row, ['ecart_type_de_l_ips_voie_gt']),
              stddev_pro: pickNumber(row, ['ecart_type_de_l_ips_voie_pro']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to fetch lycée IPS');
        }
      }
    );
  • Input schema using Zod: school (optional), school_year (optional), commune (optional), limit (default 50, max 200)
    {
      school: z.string().optional().describe('School name prefix match'),
      school_year: z.string().optional().describe('School year (rentrée), format YYYY-YYYY (e.g. "2022-2023")'),
      commune: z.string().optional().describe('Commune name prefix match'),
      limit: z.number().int().min(1).max(200).default(50).describe('Max rows to return (1-200, default 50)'),
    },
  • buildWhere helper used to construct ODSQL WHERE clause from optional conditions
    export function buildWhere(
      conditions: Array<string | undefined | null | false>
    ): string | undefined {
      const valid = conditions.filter((condition): condition is string => Boolean(condition));
      return valid.length > 0 ? valid.join(' AND ') : undefined;
    }
  • pickNumber helper used to extract numeric IPS values from API response records
    export function pickNumber(
      record: RecordObject,
      candidates: string[]
    ): number | undefined {
      const value = pickValue(record, candidates);
      if (typeof value === 'number' && Number.isFinite(value)) {
        return value;
      }
      if (typeof value === 'string' && value.trim() !== '') {
        const parsed = Number(value);
        return Number.isFinite(parsed) ? parsed : undefined;
      }
      return undefined;
    }
Behavior5/5

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

Without annotations, the description fully discloses that it returns multiple IPS values (GT, pro, combined) with standard deviations, and explains the meaning of higher IPS. It does not hide any behavioral details.

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 moderately concise; it uses four sentences that each add value. Could be slightly shorter but is not overly verbose.

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 no output schema, the description thoroughly explains the return fields (school year, UAI, name, etc.) and the unique aspect of separate tracks. It provides sufficient context for correct use.

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?

Schema coverage is 100%, so baseline 3. The description does not add extra meaning to individual parameters beyond what the schema already provides.

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 IPS for high schools (lycées) in La Réunion, specifying it is different from colleges by providing separate IPS per track. This distinguishes it from the sibling tool 'reunion_get_college_ips'.

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 implies usage for high school IPS and contrasts with colleges, but does not explicitly state when not to use it or list alternative tools. However, the context is clear enough for an 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