Skip to main content
Glama

ParliamentOS – Bundestag, Landtage, Nationalrat, EU

Hauseffekte der Umfrageinstitute

get_umfrage_hauseffekt
Read-onlyIdempotent

Hauseffekt je Umfrageinstitut und Partei für den Bundestag (Kennzahl B5): mittlere Abweichung eines Instituts vom Konsens aller ANDEREN Institute im selben Zeitfenster (±14 Tage, letzte zwei Jahre) in Prozentpunkten, dazu die Streuung. Positiv = das Institut misst die Partei höher als der Rest. Reine Statistik ohne Personenbezug; sagt nichts über Richtigkeit, nur über systematische Abstände. Optional nach partei oder institut filtern. Quelle: dawum.de (ODbL 1.0). Professional+ Tier. [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": "get_umfrage_hauseffekt"
  }
}

Input Schema

NameRequiredDescriptionDefault
parteiNoOptional: Parteikürzel wie bei dawum, z. B. 'CDU/CSU', 'SPD', 'AfD', 'Grüne', 'Linke', 'BSW', 'FDP', 'Sonstige'
institutNoOptional: Institutsname oder Teil davon, z. B. 'INSA', 'Forsa', 'Allensbach'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses the data source (dawum.de, ODbL 1.0), the access tier (Professional+), the aggregation window (±14 days, last two years), the sign convention ('Positiv = das Institut misst die Partei höher'), and an explicit no-personal-data / no-correctness-claim caveat. That is substantially more behavioral context than the annotations supply.

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 metric definition is front-loaded and dense with no filler; the sign convention and caveat follow logically. The bracketed '[Ohne KI: liefert ausschließlich Originaldaten aus amtlichen Quellen.]' boilerplate is not load-bearing for tool selection and slightly muddies the sourcing story, keeping it from a 5.

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 still explains what is returned (deviation in percentage points plus Streuung) and how to read the sign, so an agent can interpret results. Source, license, tier, and time window are all covered for a two-parameter read-only lookup.

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 both parameters already carry format examples ('CDU/CSU', 'INSA'), so the baseline is 3. The description only restates that filtering by Partei or Institut is optional and adds no syntax, matching behavior, or edge-case detail 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?

The description names the exact metric (Kennzahl B5), the entities it spans (je Umfrageinstitut und Partei für den Bundestag), and defines it operationally: mean deviation of one institute from the consensus of all OTHER institutes in the same ±14-day window over the last two years, in percentage points, plus dispersion. An agent knows precisely what data comes back and how it differs from an aggregate like get_umfrage_schnitt.

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?

It states that partei and institut can be used as optional filters, which implies the unfiltered call returns all institutes. However, it never says when to prefer this over sibling tools such as get_umfrage_schnitt or get_aktuelle_umfragen, and gives no exclusions. The interpretive caveat ('sagt nichts über Richtigkeit') is helpful framing but not usage routing.

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.