Skip to main content
Glama

ParliamentOS – Bundestag, Landtage, Nationalrat, EU

Angenommene EU-Texte suchen

search_eu_angenommene_texte
Read-onlyIdempotent

Durchsucht die vom Europaparlament ANGENOMMENEN Texte (Entschließungen, legislative Standpunkte) ab 2014 — die belastbare Antwort auf 'was hat das Parlament zu diesem Thema früher beschlossen'. Wichtig zur Einordnung gegenüber search_eu_speeches: Plenarreden liegen erst ab 09/2021 vor, angenommene Texte reichen sieben Jahre weiter zurück. query='Lieferkette' sucht im Titel und liefert dazu wörtliche Passagen aus dem deutschen Amtsblatt-Volltext (auch bei anderer Wortwahl oder englischem Begriff, sobald die Bedeutungssuche freigeschaltet ist), procedure='2023-0053' liefert die Texte zu einem Dossier, eurovoc='5595' filtert auf ein Sachgebiet — Sachgebiete sind stabiler als Stichwörter, weil dieselbe Sache über zehn Jahre unterschiedlich benannt wird. Gibt Datum, Wahlperiode, Titel, Verfahren und Registerfundstelle zurück. Wörtliche Zitate prüft pruefe_belege gegen den deutschen Amtsblatt-Volltext (Quelle: EUR-Lex/Cellar, Beschluss 2011/833/EU); wo er noch fehlt, nur Titel, Datum und TA-Nummer. 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_angenommene_texte"
  }
}

Input Schema

NameRequiredDescriptionDefault
termNoOptional: Wahlperiode — 8 (2014–2019), 9 (2019–2024), 10 (seit 2024)
limitNoAnzahl Ergebnisse, max. 40. Standard: 10
queryNoSuchbegriff im Titel, z. B. 'Führerschein', 'Lieferkette', 'Künstliche Intelligenz'
date_toNoOptional: Datum bis (ISO)
eurovocNoOptional: EuroVoc-Sachgebiets-ID, z. B. '5595'. Findet thematisch Verwandtes auch bei abweichender Benennung.
date_fromNoOptional: Datum ab (ISO)
procedureNoOptional: Verfahrenskennung im Format '2023-0053' (wie eu_procedures.process_id)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world, so the safety profile is covered; the description adds real substance on top: the 2014 coverage floor, per-hit Beleg-IDs, verification via pruefe_belege against the German Official Journal full text, and the degraded fallback (title, date and TA number only) where full text is missing. Minor gap: no pagination or result-ordering behavior is described, though limit is capped at 40.

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 and sibling differentiation are front-loaded and every parameter example earns its place, but the citation instruction is stated twice in near-identical form ("Zitiere mit genau dieser ID" then "zitiere mit Kennung und beiden Links wie in der Server-Anleitung"), and the trailing "[Ohne KI: ...]" tag adds little for an agent. Dense single block rather than structured sentences.

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 7-parameter search tool with no output schema, the description is unusually complete: it enumerates returned fields (date, electoral term, title, procedure, register reference), states the citation contract and the verification path, and flags the full-text fallback. The only shortfall is missing guidance on result volume, ranking or pagination.

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 baseline is 3; the description goes beyond it by explaining what query actually does (title search that also returns verbatim passages from the German full text, including under different wording once semantic search is enabled), why eurovoc is more stable than keywords, and that procedure follows the eu_procedures.process_id format. term, date_from/date_to and limit get no narrative beyond 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?

Specific verb plus resource plus scope: it searches the European Parliament's ADOPTED texts (resolutions, legislative positions) from 2014 onward. It also frames the concrete question the tool answers ("was hat das Parlament zu diesem Thema früher beschlossen") and explicitly contrasts itself with search_eu_speeches by coverage window, so an agent can pick it without opening a schema.

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?

It names the alternative (search_eu_speeches) and the condition that separates them: plenary speeches only go back to 09/2021, adopted texts reach seven years further. It also gives per-intent routing advice — query for title keyword search, procedure for a dossier, eurovoc for a subject area — and explains why eurovoc beats keywords for long-horizon topics.

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.