polradar

search

Dokumente suchen (Volltext + Vektor) oder nur nach Filtern auflisten (neueste zuerst). Antworten aus polradar belegen jede Aussage mit polradar_url als Markdown-Link (siehe belegregel im Ergebnis), nicht mit der Original-URL.

    source: dip | lobbyregister | abgeordnetenwatch | rss | eu (EU-Gesetzgebungsverfahren zu
    EU-Vorlagen des Bundestages, aus EUR-Lex).
    source_type: z. B. vorgang, drucksache, plenarprotokoll, register_entry, poll, article,
    rede (eine Rede aus einem Plenarprotokoll), schriftliche_frage (Frage mit Antwort),
    haushalt (ein Kapitel bzw. Einzelplan aus einem Entwurf zum Bundeshaushaltsplan).
    Namentliche Abstimmungen: source="abgeordnetenwatch", source_type="poll" – das Ergebnis
    nach Fraktion liefert danach get_document. Eine query mit „Abstimmung“/„abgestimmt“
    bringt passende Abstimmungen auch ohne diese Filter nach oben.
    date_from/date_to: YYYY-MM-DD. topic: Themen-Slug (z. B. energie, rente, migration).
    actor_id: nur Dokumente mit Bezug zu diesem Akteur (siehe find_actor).
    Ohne query muss mindestens ein Filter gesetzt sein.
    offset: zum Weiterblättern den Wert next_offset aus dem vorigen Ergebnis übergeben
    (limit bis 30). Mit query werden nur die ~200 besten Kandidaten gerankt; für vollständige
    Listen besser ohne query nur mit Filtern (Zeitraum, Quelle, Thema, Akteur) blättern –
    dort nennt total die Gesamtzahl.

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	No
`topic`	No
`offset`	No
`source`	No
`date_to`	No
`actor_id`	No
`date_from`	No
`source_type`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 12, 2026

TDQS

A4.5/5.0

Behavior4/5

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

No annotations exist, so the description carries the full burden and delivers real behavioral detail: the ~200-candidate ranking cap with query, the total count only in filter mode, the limit ceiling of 30, and the citation rule that results must be linked via polradar_url rather than the original URL. It omits auth/permission requirements, which keeps it short of a 5.

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?

Front-loaded with the core action before citation rules and per-parameter notes; each sentence carries operational content. It is dense and slightly sprawling, but no sentence is filler.

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?

An output schema exists so return values need no explanation, and the description still covers every parameter plus the cross-tool paths. The only gap is default values and any note on error behavior when no filter is supplied.

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 0% across 9 parameters, and the description compensates by defining source enum values, source_type examples, date format (YYYY-MM-DD), topic slug examples, actor_id cross-reference to find_actor, and offset/limit semantics. It does not explain the limit default of 10 or offset default of 0, so it is strong but not exhaustive.

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?

The first sentence names a specific verb and resource ('Dokumente suchen (Volltext + Vektor)') and explicitly covers the alternate mode ('oder nur nach Filtern auflisten'). It also distinguishes itself from siblings by routing actor filtering to find_actor and deferring vote results to get_document.

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?

Explicit conditions are given: 'Ohne query muss mindestens ein Filter gesetzt sein', query mode ranks only ~200 candidates while filter-only listing gives complete results with total, and offset paging uses next_offset. The namentliche Abstimmungen path is spelled out with exact source/source_type values and a query fallback.

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

All polradar tools Inspect

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

Need Help?