Skip to main content
Glama
musaceylan

PriceAtlas MCP Server

by musaceylan

run_connectors

Fetch fresh price data for products across multiple retailers by executing all available connectors with a barcode and country code.

Instructions

Run all price data connectors (Open Food Facts, Kroger, Walmart, REWE, Migros, A101) to fetch fresh prices for a product in a specific country. Saves results to the database.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
barcodeYesProduct barcode (8-14 digits)
country_codeYes2-letter country code

Implementation Reference

  • The 'run_connectors' tool is registered and its logic is implemented directly within the server.tool handler in src/index.ts. It calls the /api/connectors/run endpoint.
    server.tool(
      'run_connectors',
      'Run all price data connectors (Open Food Facts, Kroger, Walmart, REWE, Migros, A101) to fetch fresh prices for a product in a specific country. Saves results to the database.',
      {
        barcode: z.string().describe('Product barcode (8-14 digits)'),
        country_code: z.string().length(2).describe('2-letter country code'),
      },
      async ({ barcode, country_code }) => {
        try {
          const result = await api('/api/connectors/run', {
            method: 'POST',
            headers: { 'Content-Type': 'application/json' },
            body: JSON.stringify({ barcode, country_code }),
          });
          return text(result);
        } catch (e) {
          return errorResult(`Run connectors failed: ${(e as Error).message}`);
Behavior4/5

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

Strong disclosure given zero annotations: reveals write behavior ('saves to database'), lists all 6 external API dependencies, and clarifies this fetches 'fresh' (real-time) data. Missing: failure handling (what if one connector fails?), timeout behavior for multiple API calls, whether operation is idempotent, or if it overwrites existing DB records.

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 dense sentences zero waste. First sentence front-loads action and enumerates specific connectors + scope; second sentence discloses critical side effect (DB persistence). No redundancy with structured fields.

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

Completeness3/5

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

Adequate for a 2-parameter tool, but gaps remain: no output schema exists, yet description doesn't specify what the tool returns (price objects? success boolean?). Given this calls 6 external APIs, should mention timeout risks or partial failure behavior. However, database persistence and connector enumeration provide sufficient context for basic invocation.

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% (both barcode and country_code fully described in JSON schema), establishing baseline 3. Description provides contextual mapping ('for a product in a specific country') but adds no syntax, format, or constraint details 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?

Excellent specificity: verb 'Run' + resource 'price data connectors' + explicit scope (6 named sources: Open Food Facts, Kroger, etc.). The phrase 'Saves results to the database' clearly distinguishes this from sibling 'get_prices' (which presumably reads cached data) by establishing this as a fetch-and-persist operation.

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?

Implies distinction from cached retrieval via 'fetch fresh prices' and 'saves to database', but provides no explicit when-to-use guidance versus siblings like get_prices or submit_price. No mention of prerequisites (e.g., product must exist in system) or when NOT to use (e.g., rate limit concerns).

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/musaceylan/priceatlas-mcp'

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