Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_search_feder_beneficiaries

Search European Regional Development Fund beneficiaries in La Réunion by keyword, commune, or category. Returns operation details including funding amounts and location for transparency and regional analysis.

Instructions

Search beneficiaries of the European Regional Development Fund (FEDER / ERDF) 2014-2020 programming period in La Réunion. Returns funded operations: beneficiary name, operation title and summary, start/end dates, total eligible expenditure (EUR), EU contribution (EUR), location (postal code, city), intervention category (e.g. R&D, infrastructure, SMEs, environment). Sorted by start date descending. Useful to map EU-funded projects, audit transparency, or analyze regional development patterns.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoFree-text search across beneficiary name, operation title, summary
communeNoCity/commune name prefix match
categoryNoIntervention category prefix match. Examples: "Recherche et innovation", "PME", "Économie à faibles émissions", "Infrastructures de transport"
limitNoMax operations to return (1-200, default 50)

Implementation Reference

  • The async handler function that executes the 'reunion_search_feder_beneficiaries' tool logic. It queries the FEDER dataset via client.getRecords, builds a WHERE clause from optional filters (query/commune/category), orders by start date descending, limits results, and maps fields (beneficiary, operation, summary, dates, expenditure, EU contribution, location, intervention category). Returns total_operations and operations array, or an error.
    async ({ query, commune, category, limit }) => {
      try {
        const data = await client.getRecords<RecordObject>(DATASET_FEDER, {
          where: buildWhere([
            query ? `search(${quote(query)})` : undefined,
            commune ? `ville LIKE ${quote(`${commune}%`)}` : undefined,
            category ? `categorie_d_intervention_category_of_intervention LIKE ${quote(`${category}%`)}` : undefined,
          ]),
          order_by: 'date_de_debut_de_l_operation_start_date DESC',
          limit,
        });
        return jsonResult({
          total_operations: data.total_count,
          operations: data.results.map((row) => ({
            beneficiary: pickString(row, ['nom_du_beneficiaire_beneficiary']),
            operation: pickString(row, ['nom_de_l_operation_operation']),
            summary: pickString(row, ['resume_de_l_operation_summary']),
            start_date: pickString(row, ['date_de_debut_de_l_operation_start_date']),
            end_date: pickString(row, ['date_de_fin_de_l_operation_end_date']),
            total_eligible_eur: pickNumber(row, ['total_des_depenses_eligibles_total_eligible_expenditure']),
            eu_share_eur: pickNumber(row, ['ue']),
            postal_code: pickString(row, ['cp']),
            city: pickString(row, ['ville']),
            intervention_category: pickString(row, ['categorie_d_intervention_category_of_intervention']),
          })),
        });
      } catch (error) {
        return errorResult(error instanceof Error ? error.message : 'Failed to search FEDER');
      }
    }
  • Zod schema defining the input parameters: query (optional string), commune (optional string), category (optional string with examples), and limit (optional integer 1-200 default 50).
    {
      query: z.string().optional().describe('Free-text search across beneficiary name, operation title, summary'),
      commune: z.string().optional().describe('City/commune name prefix match'),
      category: z.string().optional().describe('Intervention category prefix match. Examples: "Recherche et innovation", "PME", "Économie à faibles émissions", "Infrastructures de transport"'),
      limit: z.number().int().min(1).max(200).default(50).describe('Max operations to return (1-200, default 50)'),
    },
  • Registration of the tool via server.tool() call with name 'reunion_search_feder_beneficiaries', description, schema, and handler, within the registerEconomyTools function.
    server.tool(
      'reunion_search_feder_beneficiaries',
      'Search beneficiaries of the European Regional Development Fund (FEDER / ERDF) 2014-2020 programming period in La Réunion. Returns funded operations: beneficiary name, operation title and summary, start/end dates, total eligible expenditure (EUR), EU contribution (EUR), location (postal code, city), intervention category (e.g. R&D, infrastructure, SMEs, environment). Sorted by start date descending. Useful to map EU-funded projects, audit transparency, or analyze regional development patterns.',
      {
        query: z.string().optional().describe('Free-text search across beneficiary name, operation title, summary'),
        commune: z.string().optional().describe('City/commune name prefix match'),
        category: z.string().optional().describe('Intervention category prefix match. Examples: "Recherche et innovation", "PME", "Économie à faibles émissions", "Infrastructures de transport"'),
        limit: z.number().int().min(1).max(200).default(50).describe('Max operations to return (1-200, default 50)'),
      },
      async ({ query, commune, category, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_FEDER, {
            where: buildWhere([
              query ? `search(${quote(query)})` : undefined,
              commune ? `ville LIKE ${quote(`${commune}%`)}` : undefined,
              category ? `categorie_d_intervention_category_of_intervention LIKE ${quote(`${category}%`)}` : undefined,
            ]),
            order_by: 'date_de_debut_de_l_operation_start_date DESC',
            limit,
          });
          return jsonResult({
            total_operations: data.total_count,
            operations: data.results.map((row) => ({
              beneficiary: pickString(row, ['nom_du_beneficiaire_beneficiary']),
              operation: pickString(row, ['nom_de_l_operation_operation']),
              summary: pickString(row, ['resume_de_l_operation_summary']),
              start_date: pickString(row, ['date_de_debut_de_l_operation_start_date']),
              end_date: pickString(row, ['date_de_fin_de_l_operation_end_date']),
              total_eligible_eur: pickNumber(row, ['total_des_depenses_eligibles_total_eligible_expenditure']),
              eu_share_eur: pickNumber(row, ['ue']),
              postal_code: pickString(row, ['cp']),
              city: pickString(row, ['ville']),
              intervention_category: pickString(row, ['categorie_d_intervention_category_of_intervention']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to search FEDER');
        }
      }
    );
  • Dataset constant DATASET_FEDER = 'liste_des_operations_31' pointing to the OpenDataSoft dataset for FEDER beneficiaries.
    const DATASET_FEDER = 'liste_des_operations_31';
  • The buildWhere, jsonResult, errorResult, pickNumber, pickString, and quote helper functions imported by the handler from src/utils/helpers.ts.
     */
    export function jsonResult(data: unknown): ToolResult {
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(data, null, 2),
          },
        ],
      };
    }
    
    /**
     * Format error as tool result
     */
    export function errorResult(message: string): ToolResult {
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({ error: message }, null, 2),
          },
        ],
      };
    }
    
    /**
     * Build ODSQL WHERE clause from conditions
     */
    export function buildWhere(
Behavior4/5

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

With no annotations provided, the description carries full burden. It discloses that results are sorted by start date descending and specifies the returned data fields. While it does not cover rate limits or pagination details, the behavioral description is reasonably thorough for a search tool.

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 two sentences long, efficiently packing purpose, scope, returned fields, and sorting order. It is well-structured and free of unnecessary words, though it could be slightly more scannable.

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?

Given the absence of an output schema, the description adequately details the returned fields. It covers the dataset scope, search capabilities, and sorting. It is complete enough for an agent to understand what the tool returns and when to use it.

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% with each parameter already described. The description adds minimal extra meaning—for example, listing examples for the category parameter. Baseline is 3, and no significant additional semantics are provided.

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 identifies the tool's purpose: searching beneficiaries of the European Regional Development Fund (FEDER/ERDF) for the 2014-2020 period in La Réunion. It lists the specific fields returned, distinguishing it from many sibling search tools that target different datasets.

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 states it is 'useful to map EU-funded projects, audit transparency, or analyze regional development patterns,' which implies usage context. However, it does not explicitly mention when to avoid this tool or compare it to alternative tools for similar queries.

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