Skip to main content
Glama

ParliamentOS – Bundestag, Landtage, Nationalrat, EU

EU-Transparenzregister suchen

search_eu_lobby
Read-onlyIdempotent

Sucht Organisationen im EU-Transparenzregister und zeigt, wie oft sie sich mit der EU-Kommission getroffen haben — sortiert nach Treffen. Der Parameter topic filtert vorrangig auf dem AMTLICHEN Politikfeld des Registers (40 Werte, von jeder Organisation selbst angegeben, im Register vollständig befüllt): 'Energy', 'Climate action', 'Environment', 'Transport', 'Public health', 'Digital economy and society', 'Taxation', 'Trade', 'Agriculture and rural development', 'Research and innovation' u. a. Deutsche Begriffe wie 'Energie', 'Klima', 'Verkehr', 'Gesundheit' werden erkannt. Lässt sich der Begriff keinem Feld zuordnen, fällt die Suche auf eine Freitextsuche über Name und Selbstbeschreibung zurück und sagt das ausdrücklich — diese Trefferzahl ist dann eine Suchtreffer-Zahl und keine Aussage über tatsächliche Lobbytätigkeit. Erfasst sind nur Treffen mit der EU-Kommission, nicht mit Parlament oder Rat: Kommissar-Kabinette ab 12/2014 (Juncker, von der Leyen I und die laufende Kommission) und Generaldirektionen ab 12/2014. Jeder Treffer trägt eine Beleg-ID [[beleg:…]]. Zitiere mit genau dieser ID; die fertige Antwort ist mit pruefe_belege prüfbar. Jeder Treffer nennt am Ende der Antwort Kennung, Beleg-Seite und Original; zitiere mit Kennung und beiden Links wie in der Server-Anleitung. [Ohne KI: liefert ausschließlich Originaldaten aus amtlichen Quellen.]

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_lobby"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoAnzahl Ergebnisse, max. 25. Standard: 10
topicNoOptional: Thema oder Suchbegriff, z. B. 'Wasserstoff', 'Pharma', 'Automobil' (sucht in Name und Zielbeschreibung)
betreffNoOptional: Suchbegriff im Betreff der Kommissionstreffen (englisch), z. B. 'due diligence', 'supply chain', 'AI Act'. Liefert die Organisationen, die zu diesem Betreff Treffen hatten, sortiert nach Zahl dieser Treffen. Für die Lobbyarbeit zu einem Dossier.
countryNoOptional: ISO2-Sitzland, z. B. 'BE', 'DE', 'US'. Achtung: EU-Dachverbände sind fast immer in Belgien registriert, nicht im Herkunftsland ihrer Mitglieder.
min_meetingsNoOptional: nur Organisationen mit mindestens so vielen dokumentierten Kommissions-Lobbytreffen

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only supply the generic read-only/idempotent profile, and the description adds substantial behaviour on top: the topic filter resolves against the officially self-reported policy field first, degrades to free-text search on name and description, and explicitly warns that such a hit count is not evidence of lobbying activity. It also discloses data coverage boundaries (Commission only, from 12/2014, cabinets plus DGs) and the fact that each hit carries a [[beleg:…]] ID that is verifiable via pruefe_belege — real operational context, not a restatement of annotations.

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 is front-loaded in the first clause, which is good, but the single dense paragraph then mixes in ten enumerated policy-field examples plus citation etiquette ('Zitiere mit genau dieser ID … wie in der Server-Anleitung') that belongs in server instructions, and a trailing '[Ohne KI: …]' disclaimer. Both are selection-irrelevant payload that dilutes the retrieval cues.

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 five optional parameters, no output schema and no required arguments, the description supplies everything the other dimensions do not operate on: result ordering, per-hit provenance (Kennung, Beleg-Seite, Original links), the meaning of a fallback hit count, and the dataset's time and institutional boundaries. Nothing an agent needs in order to call this correctly and interpret the results is missing.

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 genuinely deepens `topic`: it names the underlying 40-value register taxonomy, gives example values, notes that German synonyms ('Energie', 'Klima') are mapped, and explains the free-text fallback. The only blemish is a mismatch with the schema's own wording, which says topic 'sucht in Name und Zielbeschreibung' while the description says it filters primarily on the official policy field — an agent could be briefly confused about which semantics apply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb, resource and output shape: organizations from the EU Transparency Register, ranked by how many meetings they had with the EU Commission. An agent knows exactly what comes back (ranked list of organisations). It does not, however, draw a line against plausible siblings such as search_lobby (national lobby register) or get_eu_lobby_network, so the differentiation requirement for a 5 is unmet.

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?

Scope is stated clearly enough to imply usage (only Commission meetings, not Parliament or Council; cabinet-level from 12/2014, DGs from 12/2014), and the fallback behaviour of the topic filter is explained. But there is no explicit 'use this instead of X when Y' routing against any of the ~30 sibling search tools provided, so the agent must infer the choice from the title alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.