Skip to main content
Glama

finwire.pl - Polish financial data

UOKiK and KNF fines of Polish banks

get_bank_penalties
Read-onlyIdempotent

Use for fines imposed by UOKiK or KNF on a Polish bank, how many fines a bank had in the last 5 years and the sum, or which banks were fined most. For the KNF warnings list of unlicensed firms, use check_knf_warnings. For the BFG deposit guarantee, use check_bfg_guarantee. Fines imposed by the President of UOKiK (consumer protection) and by the Polish Financial Supervision Authority (KNF) on Polish banks described on finwire.pl, in the last 5 years: count and sum per bank (series finwire_bank_penalty_count; group companies such as mortgage banks, fund managers or leasing firms counted separately). With bank: the fines of that bank with the party verbatim from the source, amount (UOKiK press releases often give rounded amounts), dates, finality when the press release states it, and a link to the UOKiK press release or the KNF list. Matching uses current and former legal names (e.g. Santander Bank Polska = Erste Bank Polska); parties matched with lower confidence are left out. UOKiK fines start from the first press release read (the RSS feed has no history). Information only, not an assessment of the bank.

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_bank_penalties"
  }
}

Input Schema

NameRequiredDescriptionDefault
bankNoBank page slug on finwire.pl, e.g. pko-bp, mbank, ing, pekao, erste, millennium, alior, bnp-paribas, credit-agricole, velobank; omit for all banks.
limitNoFines to list for the bank, default 20.

Output Schema

NameRequiredDescriptionDefault
urlYes
asOfNo
dataNo
titleYes
sourceYes
docsUrlYes
licenseYes
summaryYes
citationYes
datasetIdYes
sourceUrlNo
truncatedNo
serverDateYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive), yet the description still adds substantive behavior: source of record (finwire.pl), a 5-year window, separate counting of group companies, entity matching by current and former legal names with low-confidence matches dropped, rounded amounts from UOKiK press releases, and coverage that starts at the first RSS press release with no history. The only missing piece is result shape/pagination, which the output schema covers.

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 use case and sibling routing before the detail, and every clause carries information. It is dense and slightly repetitive — the finwire.pl/UOKiK-KNF framing is restated after the first sentence — but nothing is padding.

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?

For a two-parameter read-only tool with an output schema, the description covers everything an agent needs: what is counted, the time window, entity-matching rules, known data caveats, and the aggregate-vs-detail modes. Return values are correctly left to the 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 met by the schema alone; the description still adds meaning by spelling out what supplying `bank` yields (verbatim party name, amount, dates, finality when stated, source link) versus the per-bank aggregate series returned without it. The slug-format advice stays in the schema, which is fine.

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 resource (UOKiK/KNF fines on Polish banks) and a specific set of supported questions: per-bank counts, 5-year sums, and rankings. It explicitly names the siblings it is not (check_knf_warnings for unlicensed-firm warnings, check_bfg_guarantee for deposit guarantees), so an agent can route without opening any 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?

Gives explicit positive triggers (fine totals, most-fined banks, a single bank's fines) and explicit exclusions mapped to the correct alternative tool. The two calling modes — omit bank for aggregates, supply bank for detail — are described rather than left to inference.

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.