Skip to main content
Glama

Prawnet: Polish case law and legislation

Jak orzekają sądy — wyniki spraw

jak_orzekaja_sady
Read-onlyIdempotent

Jak kończą się w I instancji sprawy jednej kategorii, osobno wg tego, kto kogo pozwał: kredyty walutowe (frankowe), klauzule niedozwolone w umowach konsumenckich, szkoda na osobie (zadośćuczynienie, odszkodowanie). Zwraca liczby wyroków uwzględniających powództwo w całości, w części i oddalających, udziały procentowe z przedziałem Wilsona 95 %, n, okres (lata wyroków), podział na szczeble (sąd rejonowy / okręgowy), lata, do 10 sądów (od 30 wyroków) i do 5 przykładowych wyroków z linkami. Dane: wyroki opublikowane w SAOS z etykietą rozstrzygnięcia o wysokiej pewności; typ stron (osoba / firma / instytucja) rozpoznany regułami, bez nazw stron i statystyk sędziów. To rozkład wyników opublikowanych wyroków, nie szansa wygrania sprawy (ugody i cofnięcia nie są liczone). Bez filtrów okresu i szczebla liczby są te same co na prawnet.pl/jak-orzekaja-sady.

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": {
      "kategoria": "<kategoria>"
    },
    "name": "jak_orzekaja_sady"
  }
}

Input Schema

NameRequiredDescriptionDefault
sadNoNazwa sądu ("SO w Olsztynie"); tylko sądy z ≥ 30 wyrokami w kategorii. Do 120 znaków
rok_doNoOstatni rok wyroków (włącznie)
rok_odNoPierwszy rok wyroków (włącznie)
kierunekNoKto pozwał: pozwy_osob (osoba fizyczna przeciw firmie lub instytucji), pozwy_firm (firma przeciw osobie — oddalenie = wygrana osoby). Pominięte = oba osobno
szczebelNoSąd I instancji: SR, SO, inne
kategoriaYeskredyt_walutowy (indeksowane / denominowane), klauzule_konsumenckie (inne klauzule niedozwolone; obie art. 385¹ k.c.), szkoda_osobowa (art. 444–446 k.c.)

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/closed-world, and the description adds substantial behavior on top: provenance (SAOS with high-confidence outcome labels), rule-based party typing, explicit exclusions (no party names, no judge statistics, settlements and withdrawals not counted), output caps (up to 10 courts, up to 5 example rulings with links), and Wilson 95% intervals. It also pre-empts the most likely misuse by stating this is a distribution, not a win probability.

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 key framing — first-instance outcome distribution by category and suing party — is front-loaded, and most of the dense middle sentence is substantive. The paragraph is long and packs output details (courts, sample rulings, intervals) that the output schema already conveys, and the prawnet.pl comparison is a nice anchor but somewhat extended.

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?

Given six parameters, an output schema, and full annotation coverage, nothing an agent needs to call this correctly is missing: category semantics, direction semantics, court-level filtering, data provenance, and interpretation caveats are all present. Return values are already carried by the output schema, so the description need not repeat them.

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 three parameters carry enums, so the schema already documents each parameter thoroughly, including the 'oddalenie = wygrana osoby' interpretation for kierunek and the ≥30-verdict threshold for sad. The description restates some of this (court threshold, direction split) but adds no new format or semantic detail. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific question — how first-instance cases in one category end, split by who sued whom — and enumerates the three covered categories (currency loans, abusive clauses, personal injury). The resource and output shape are unambiguous. It stops short of naming a specific sibling it should be preferred over, so sibling differentiation is only implicit via the 'distribution of published rulings, not win probability' framing.

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?

Usage context is implied rather than stated: the description explains what the numbers mean and that with no period/chamber filters results match prawnet.pl, which hints at when to use it for baseline outcome statistics. There is no explicit 'use this when X, use sibling Y when Z' guidance, and no stated preconditions such as the minimum-verdict threshold for filters beyond what the schema already says.

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.

Resources