Skip to main content
Glama

ParliamentOS – Bundestag, Landtage, Nationalrat, EU

EU-Kohäsionsförderung

get_eu_cohesion_funding
Read-onlyIdempotent

Zeigt EU-Kohäsionsfonds-Projekte (EFRE/ESF+/Kohäsionsfonds/JTF) für Deutschland und Österreich. Zwei Förderperioden verfügbar: 2021-2027 (Standard, laufend — inkl. Gemeindeebene) und 2014-2020 (abgeschlossen). Modi: 'regions' (NUTS3-Ranking), 'projects' (Einzelprojekt-Suche), oder 'wahlkreis' (politische Wahlkreis-Ebene — für Deutschland volle Bundestagswahlkreis-Ebene mit 299 Wahlkreisen, für Österreich nur Landeswahlkreis-Ebene = Bundesland, da Österreichs NUTS3-Ebene gröber als der politische Bezirk ist und eine eindeutige Regionalwahlkreis-Zuordnung daraus nicht möglich ist). Deckt nur EU-kofinanzierte Projekte ab, nicht den gesamten Länderhaushalt. [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_eu_cohesion_funding"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'regions' (Standard) für NUTS3-Ranking, 'projects' für Einzelprojekt-Suche, 'wahlkreis' für Wahlkreis-/Landeswahlkreis-Ebene
limitNoAnzahl Ergebnisse, max. 30. Standard: 10
queryNoNur bei mode='projects': Suchbegriff im Projektnamen oder Empfängernamen
periodNoFörderperiode: '2021-2027' (Standard, laufend) oder '2014-2020' (abgeschlossen). Die Perioden werden NIE zusammengezählt — sie sind fachlich nicht addierbar.
countryNoOptional: 'Germany' oder 'Austria'. Ohne Angabe: beide (außer bei mode='wahlkreis', dort erforderlich).
bundeslandNoBei mode='wahlkreis' und country='Austria': Bundesland/Landeswahlkreis, z. B. 'Wien', 'Steiermark'. Bei mode='regions': filtert das NUTS3-Ranking auf ein deutsches oder österreichisches Bundesland, z. B. 'Sachsen'.
nuts3_codeNoBei mode='projects': Projektfilter; bei mode='regions': grenzt das Ranking auf genau diese Region ein. Z. B. 'DE40A', 'AT312'
wahlkreis_nrNoNur bei mode='wahlkreis' und country='Germany': Bundestagswahlkreis-Nummer (1-299). Ohne Angabe: Ranking aller Wahlkreise.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely behavioral context beyond that: the periods are never summed because they are not additive, Austria's NUTS3 level is coarser than its political districts so constituency mapping is impossible, and data comes exclusively from official sources without AI processing. These are substantive expectations an agent could not infer from schema or annotations.

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 opening sentence establishes resource and geography before drilling into periods and modes, so it is well front-loaded. The long nested parenthetical on Austrian constituency granularity is dense but functional; the trailing '[Ohne KI: ...]' provenance note is the least load-bearing element for tool selection.

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 8 optional parameters, no output schema and safety already handled by annotations, the definition covers the hard part well: mode semantics, period non-additivity and the country/level constraints. What remains unexplained is the shape of returned records (fields, ranking metrics), which an agent cannot check without an output schema.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema cannot: why 'wahlkreis' behaves differently in Austria versus Germany, and the conceptual rule that the two funding periods must never be aggregated. The interaction between mode, country and bundesland is made explicit in prose.

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 states a specific verb+resource (zeigt EU-Kohäsionsfonds-Projekte), enumerates the funds covered (EFRE/ESF+/Kohäsionsfonds/JTF), the geography (Deutschland, Österreich) and the three retrieval modes. An agent knows exactly what data domain this returns and how the modes differ, and the explicit scope caveat ('nur EU-kofinanzierte Projekte, nicht den gesamten Länderhaushalt') prevents a common misreading.

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?

Mode selection is spelled out in detail ('regions' for NUTS3 ranking, 'projects' for single-project search, 'wahlkreis' for political constituency level), including the country-specific constraint that 'wahlkreis' is mandatory for Austria and that only Landeswahlkreis level is possible there. Period semantics are also disambiguated (2021-2027 standard/ongoing vs 2014-2020 completed). It stops short of naming alternative sibling tools or stating when not to use this one, but the conditional guidance is strong.

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.