Skip to main content
Glama

EU & UK Public Tenders: TED, BOAMP API, Find a Tender & Awards

search_eu_public_tenders
Read-only

Search and filter EU and French public tenders and contract awards by keyword, CPV code, country, and value; get buyers, deadlines, winners, and bid counts.

Instructions

Public tenders and contract awards in Europe (TED) and France (BOAMP, DECP) by keyword, CPV code and country: buyer, value in euros, deadline; for awards, the winner, the amount and the number of bids. Pay per result on your Apify account: run start $0.003, open tender delivered $0.003, contract award delivered $0.005.

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_eu_public_tenders"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoOpen tenders: calls for tender you can still bid on (deadline, estimated value, buyer contact, documents link). Contract awards: who won which contract, for how much and against how many bids (winners with company details).
cpvCodesNoOfficial EU procurement categories, as codes or prefixes: "72" = IT services, "48" = software packages, "45" = construction work, "79" = business services, "90" = cleaning & environment, "33" = medical equipment, "71" = architecture & engineering. The most reliable filter across languages.
keywordsNoWords or phrases searched in the title, description, lots and official category of each notice. English keywords also find notices in other languages through their official category (e.g. "software" finds German, Polish or Spanish software tenders). For French national notices (BOAMP, DECP), add French keywords too (e.g. "logiciel"). Leave empty to get everything matching the other filters.
languageNoLanguage of the CPV category labels and of the TED links. Titles and descriptions stay in their original language.
maxItemsNoMaximum number of notices in the dataset (you pay per notice). Default here: 25.
countriesNoCountries of the buyer (2-letter codes). Leave empty for all of Europe (EU, EEA, Switzerland and candidate countries).
minValueEurNoEstimated value (tenders) or awarded value (awards), converted to euros.
frenchDepartmentsNoFrance only: department numbers, e.g. "69", "75", "2A", "974". Selecting departments limits the search to France.
publishedWithinDaysNoNotices published in the last N days. For daily monitoring, 2 or 3 days is enough.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description goes beyond that by disclosing the pay-per-result cost model with exact per-item prices (run start $0.003, tender $0.003, award $0.005). That cost signal is materially useful for an agent deciding how to size maxItems, though nothing is said about auth or rate 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?

Two sentences, front-loaded with coverage and data sources, then pricing. Dense but every clause carries information; the semicolon-separated field list is slightly compressed but not wasteful.

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 read-only, 9-parameter search tool with no output schema, the description compensates by naming the returned fields (buyer, value, deadline, winner, amount, bid count) and the geographic/source scope. Only the title's 'UK / Find a Tender' coverage is left unaddressed in the body, a minor gap against an otherwise complete definition.

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% and each parameter already carries rich guidance (CPV prefixes, French department codes, country enum, language behavior), so the description's brief mention of keyword/CPV/country adds no meaning beyond it. Baseline 3 is correct when the schema does the heavy lifting.

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+resource (public tenders and contract awards) with named sources (TED, BOAMP, DECP) and named filters (keyword, CPV code, country). It also enumerates the fields returned (buyer, value, deadline, winner, bid count), so an agent can tell this apart from siblings like search_french_companies or search_uk_companies without opening the schema.

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 implied rather than stated: the description makes clear this is a procurement search covering Europe and France, but never says when to prefer it or when not to, and names no alternative tool. The only genuine usage hint ('for daily monitoring, 2 or 3 days is enough') lives in the schema, not the description.

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