Skip to main content
Glama
Sign In

Aurelmark

by io.github.Ishan73744
OverviewDiscussionsAdmin

List EU contract awards

awards_list_contracts
Read-onlyIdempotent

Returns EU public-contract winners from official TED (Tenders Electronic Daily) award notices published since a date: who won, which buyer, value, CPV and lots. Use it to find new awards or what a company has won; use awards_get_contract for one known notice, and tenders_list_deadline_changes for open tender deadlines, not winners. Inputs (all optional, they narrow together): since (YYYY-MM-DD, default 7 days ago; about 45 days are kept), cpv (up to 5 comma-separated CPV prefixes of 2 to 8 digits, e.g. 72 for IT services), country (buyer, 3-letter ISO code as TED uses, e.g. DEU), winner (name prefix, at least 3 letters, e.g. Mennica Polska), winner_id (exact official id, e.g. PL1234567890), limit (1 to 50, default 20) and cursor (next_cursor, same filters). Output: awards[] with winners, buyer, value, CPV, dates, lots, notice URL and SHA-256 proof, plus count, has_more, next_cursor and feed (checked_at, coverage). Stored observations, not a live TED search; check feed.checked_at. Terms: read-only; MCP calls are never charged. Without a key, metered routes give 10 successful answers a day free, as short samples (up to 3 records, without file proof, history or paging cursor) where a paid HTTP address exists (unmetered routes are unlimited); errors do not count. On the paid HTTP routes, errors are free, and so are empty answers except a sanctions name search with no match when every loaded list it checks is fresh (lists not loaded yet are named in the answer). An optional API key keeps its prepaid-credit policy. When the free answers run out, the error names the HTTP alternative.

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": "awards_list_contracts"
  }
}

Input Schema

NameRequiredDescriptionDefault
cpvNoCPV code or prefix, 2 to 8 digits, e.g. 72 for IT services; up to 5, comma-separated
limitNoAwards per page, 1 to 50 (default 20); e.g. 20.
sinceNoAwards published on or after this date, YYYY-MM-DD (default: 7 days ago; about 45 days are kept); e.g. 2026-10-01. Must be a parseable YYYY-MM-DD date.
cursorNoOpaque next_cursor from this tool's prior answer; a followed by 1 to 12 digits, e.g. a0. Keep filters unchanged; omit on first call.
winnerNoWinner name prefix, e.g. Mennica Polska; at least 3 normalized letters/digits; case/accent/punctuation-insensitive, normalized text truncated to 200 characters
countryNoBuyer country, 3-letter ISO code as TED uses, e.g. DEU, FRA, POL
winner_idNoWinner official identifier, e.g. PL1234567890; exact normalized match, at least 3 letters/digits; punctuation ignored and normalized key truncated to 64 characters

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, but the description still adds material behavior: these are stored observations rather than a live TED search, so callers must check feed.checked_at, and only ~45 days of history are retained. The metering/free-quota and error-charging details are real behavioral context too, though the paid-HTTP aside about a sanctions name search is irrelevant to this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose, routing and parameter guidance come first and are well ordered, but the closing paragraph on metering, paid HTTP routes and a sanctions name search is long, hard to parse, and partly off-topic for a read-only award lister. Roughly a third of the text is quota boilerplate rather than tool-specific guidance.

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?

With no output schema, the description earns credit for enumerating the return shape (awards[], count, has_more, next_cursor, feed.checked_at/coverage) and the pagination contract. Combined with coverage of all 7 optional parameters and the data-freshness caveat, an agent has everything needed to call and interpret results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds the critical combining semantics — all inputs are optional and 'narrow together' (AND, not OR) — plus the retention window on 'since' and prefix behavior for cpv/winner. The cursor note ('same filters') is also echoed usefully, though most individual field formats are already in the schema.

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 and resource with scope: EU public-contract winners from TED award notices published since a date, including the fields returned (winner, buyer, value, CPV, lots). It explicitly distinguishes itself from awards_get_contract (one known notice) and tenders_list_deadline_changes (open deadlines, not winners), so an agent can route without opening sibling schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use cases ('find new awards or what a company has won') and names two alternatives with the conditions that select them, including an explicit 'not winners' exclusion. Nothing about tool selection is left to inference.

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

All Aurelmark toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources