Skip to main content
Glama
Sign In
parlament-at

parlament-at

by bernhardbrugger
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Volltextsuche in Reden, Pressemeldungen und Gegenständen

parl_suche
Read-onlyIdempotent

Search Austrian Parliament full texts to find who said what on a topic. Verify exact quotes or filter speeches by speaker, date, and legislative period.

Instructions

Durchsucht den Volltext des Parlaments: standardmäßig alle Reden in den Plenarprotokollen (Nationalrat und Bundesrat, mit Zwischenrufen), auf Wunsch Pressemeldungen der Parlamentskorrespondenz, Verhandlungsgegenstände (Anträge, Anfragen, Gesetze) oder alles. Damit lässt sich prüfen, WER ZU WELCHEM THEMA WAS gesagt hat: modus="phrase" findet eine genaue Wortfolge (Zitate prüfen), redner="Kickl" begrenzt auf einen Redner, von/bis und gp auf einen Zeitraum. Jeder Treffer nennt Redner, Sitzung, Datum, einen Ausschnitt und die Argumente für parl_rede (kompletter Wortlaut) bzw. parl_gegenstand. Ein Treffer belegt nur, dass etwas gesagt wurde, nicht ob es stimmt. Quelle: offene Daten des Parlaments (CC BY 4.0).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "suche": "<suche>"
    },
    "name": "parl_suche"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpNoGesetzgebungsperiode: 28 oder "XXVIII" (gilt nicht für den Bundesrat)
bisNoBis zu diesem Tag (einschließlich), Format JJJJ-MM-TT
vonNoAb diesem Tag, Format JJJJ-MM-TT
limitNoAnzahl Treffer pro Aufruf
modusNoalle = alle Wörter kommen vor, beliebig = mindestens eines, phrase = genau diese Wortfolgealle
sucheYesSuchbegriffe oder eine Wortfolge, z. B. "Staatsbesuch" oder "Ich rede vom Staatsbesuch"
offsetNoTreffer überspringen (Seiten)
rednerNoNur Reden dieser Person (Name oder Teil davon, z. B. "Kickl"); prüft die ersten 300 Treffer der Suche, deshalb Suche eng fassen
bereichNoreden = Plenarprotokolle, pressemeldungen = Parlamentskorrespondenz, gegenstaende = Anträge/Anfragen/Gesetze, allesreden
gremiumNoNR = Nationalrat, BR = Bundesrat
nur_titelNoNur in Titeln suchen (bei Reden steht der Redner im Titel)
sortierungNoReihenfolge der Trefferrelevanz

Output Schema

NameRequiredDescriptionDefault
itemsYes
totalYesTotal number of hits reported by the Parliament (may be a lower bound, see the text)
offsetYesIndex of the first returned item

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/open-world, yet the description adds real value: each hit contains Redner, Sitzung, Datum, Ausschnitt and the arguments needed to fetch the full text. The epistemic caveat ("Ein Treffer belegt nur, dass etwas gesagt wurde, nicht ob es stimmt") and the CC BY 4.0 source are exactly the kind of context annotations cannot convey. It does omit the practical constraint that redner only checks the first 300 hits, which lives only in the schema.

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?

The core purpose and default scope are front-loaded in the first sentence, and the following sentences each add a distinct piece (search modes, hit contents, caveat, source). It is dense for one paragraph with 12 parameters, but there is little wasted language.

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?

With an output schema and full schema coverage, the remaining burden is explaining what a hit is good for and what it does not prove, which the description does well alongside the multi-source scope. The one meaningful gap is the redner 300-hit pre-check caveat, which materially affects how narrowly the agent should formulate suche but appears only in the schema.

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 every parameter is documented there, so the baseline is 3. The description mostly restates schema semantics (modus="phrase" = genaue Wortfolge, redner="Kickl" = Begrenzung auf eine Person) rather than adding syntax or edge-case meaning beyond it. Only the combined-usage framing (redner + von/bis + gp for a Zeitraum) adds slight value.

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 (Volltextsuche über Reden, Pressemeldungen, Verhandlungsgegenstände) and explicitly names the default scope (Plenarprotokolle NR/BR inkl. Zwischenrufe) and the optional scopes. It also distinguishes itself from siblings by naming parl_rede (Wortlaut) and parl_gegenstand as follow-up tools, so an agent can separate it from parl_reden_person or parl_gegenstaende without reading schemas.

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

Usage Guidelines4/5

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

"Damit lässt sich prüfen, WER ZU WELCHEM THEMA WAS gesagt hat" gives a concrete use case, and it immediately shows how to narrow with modus, redner, von/bis and gp. Routing to parl_rede for the full text is implied by "Argumente für parl_rede", but there is no explicit when-not-to-use (e.g. versus parl_reden_person for a pure person listing).

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

Deploy Server

Other Tools