Skip to main content
Glama
@corridordata/mcp-server

@corridordata/mcp-server

Official
by corridordata

search_global_tenders

Read-onlyIdempotent

Search live multilateral procurement tenders, RFPs, and contract awards across World Bank, UNGM, UNDP, and EU TED by keywords and countries to find bidding opportunities or winning suppliers.

Instructions

Search live multilateral procurement tenders, RFPs, EOIs, and contract awards (including winning suppliers and award prices) across World Bank, UNGM (32+ UN Agencies), UNDP, and EU TED (corridordata/multilateral-development-tenders).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_global_tenders"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourcesNoMultilateral portals to query in parallel (defaults to all 4).
keywordsNoSector or technical keywords (e.g. ['software', 'cloud', 'advisory', 'solar']).
maxItemsNoMaximum procurement or contract-award notices to return.
countriesNoTarget country names (e.g. ['Philippines', 'India', 'Kenya', 'Spain']).
recordModeNoReturn open bidding opportunities, awarded contracts, or all notices.open_tenders
maxTotalChargeUsdNoOptional per-run USD spend cap forwarded to Apify Pay-Per-Event billing (`maxTotalChargeUsd`).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds value beyond that by noting results are 'live', that sources are queried in parallel, that award records include winning suppliers and prices, and by tying maxTotalChargeUsd to Apify Pay-Per-Event billing — a real cost consideration. It does not mention result freshness/pagination limits.

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?

A single front-loaded sentence that packs source coverage, record types and the dataset identifier without filler. It is slightly dense — the parenthetical dataset slug and the award-price clause compete with the core purpose — but nothing is genuinely wasted.

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?

For a six-parameter, all-optional search tool with no output schema, the description does enough: it names what record kinds come back and what award records contain. It stops short of describing response shape, pagination, or how the four sources' results are merged, which an agent calling blind would benefit from.

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 description coverage is 100%, so every parameter including the recordMode enum and maxItems cap is already documented. The description only echoes the record types in prose and maps the cost cap to the billing model; it adds no syntax or behavioral detail beyond the schema. Baseline 3 applies.

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?

States a specific verb ('Search') plus the exact resource class (multilateral procurement tenders, RFPs, EOIs, contract awards) and enumerates the source systems: World Bank, UNGM, UNDP, EU TED. That source enumeration cleanly separates it from the country-specific siblings like search_spain_public_tenders and search_uk_france_tenders.

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?

Usage is only implied: an agent can infer this tool covers multilateral/international portals rather than national ones, but the description never states when to prefer it over the country-specific tender tools or what to do when a query spans both. No prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.