Skip to main content
Glama

Prawnet: Polish case law and legislation

Zakres bazy orzeczeń

zakres_bazy
Read-onlyIdempotent

Zakres bazy orzeczeń Prawnet dla każdego rodzaju sądu (sądy powszechne, SN, TK, KIO, NSA/WSA) i źródła (SAOS, baza UZP, trybunal.gov.pl, repozytorium2.sn.pl, CBOSA): liczba orzeczeń, daty pierwszego i ostatniego, sposób aktualizacji, znane luki i znaczenie braku trafienia przy weryfikacji sygnatury. Znane luki to m.in.: sądy powszechne i SN do 06.2016 — wybór z SAOS; NSA/WSA — wybór do 03.2025, uzupełniany importem całej CBOSA; repozytorium SN i CBOSA — postęp importu w liczbach. Z polem sad także: liczba orzeczeń wg roku wydania (ostatnie 12 lat) i — poza sądami powszechnymi — gęstość numerów spraw wg roku z sygnatury (odsetek numerów od 1 do najwyższego znanego, które mamy; górne oszacowanie kompletności) z rejestrami pełnymi TK i KIO. Liczby mierzone na bieżąco (bufor do 6 godzin), w razie awarii z dziennej migawki (liczby_zrodlo).

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": "zakres_bazy"
  }
}

Input Schema

NameRequiredDescriptionDefault
sadNoJeden rodzaj sądu (NATIONAL_APPEAL_CHAMBER = KIO, ADMINISTRATIVE = NSA/WSA); dodaje liczby wg roku. Pominięte = wszystkie, bez lat

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / sad / description
      Previous value: -"Jeden rodzaj sądu (NATIONAL_APPEAL_CHAMBER = KIO, ADMINISTRATIVE = wybór NSA/WSA); dodaje liczby wg roku. Pominięte = wszystkie, bez lat"New value: +"Jeden rodzaj sądu (NATIONAL_APPEAL_CHAMBER = KIO, ADMINISTRATIVE = NSA/WSA); dodaje liczby wg roku. Pominięte = wszystkie, bez lat"
  2. Added

TDQS

A4/5.0
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 the description correctly does not repeat the safety profile. Instead it adds genuinely non-inferable behavior: numbers are measured live with a buffer of up to 6 hours, and on failure they fall back to a daily snapshot indicated by the `liczby_zrodlo` field. What is missing is any sense of response size or cost, which matters for a statistics-returning tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single dense run-on paragraph stitched together with parentheses, dashes and semicolons, which is hard to scan despite being front-loaded with the coverage scope. Almost every clause carries substantive information (sources, gaps, freshness, parameter effects), so there is little true filler, but the structure works against fast parsing.

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?

For a multi-source coverage/stats tool, the description covers the source list, known gaps and how they were filled, freshness and fallback, and the effect of the one parameter; an output schema exists so return values need not be explained. The main residual gap is guidance on interpreting or comparing the reported numbers (e.g., what 'liczba orzeczeń' counts per source).

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 100% and the enum is already documented, so the baseline would be 3; the description goes beyond it by stating that `sad` adds per-year counts for the last 12 years and, except for COMMON courts, case-number density per year as an upper-bound completeness estimate, with full registers for TK and KIO. It also states that omitting the parameter returns all courts without year breakdowns. That is meaningful output semantics tied to the parameter, not a restatement of 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 states a concrete resource and what it reports: coverage of the Prawnet rulings database per court type (sądy powszechne, SN, TK, KIO, NSA/WSA) and per source (SAOS, UZP, trybunal.gov.pl, repozytorium2.sn.pl, CBOSA), including counts, first/last dates, update method, and known gaps. It also spells out what the optional `sad` parameter changes in the output (yearly counts, case-number density). An agent can distinguish this coverage/inventory tool from the search siblings without consulting the schema.

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: by explaining 'znaczenie braku trafienia przy weryfikacji sygnatury', it signals the tool is relevant when interpreting a no-hit during signature verification, and the known-gap list implies using it before concluding a ruling does not exist. However, it never says explicitly when to call this versus alternatives such as sprawdz_sygnature or szukaj_orzeczen, and it names no alternative or exclusion.

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