Skip to main content
Glama

Prawnet: Polish case law and legislation

Rozbieżność SN i sądów niższych

rozbieznosc_orzecznicza
Read-onlyIdempotent

Sygnał statystyczny rozbieżności w orzecznictwie do artykułu: rozkład rozstrzygnięć (oddalenie / częściowe / uwzględnienie / inne, z etykiet o wysokiej pewności) w próbce orzeczeń powołujących artykuł, wg szczebla sądu (SN, SA, SO, SR …), oraz porównanie udziału uwzględnień SN i SA+SO. flaga: sygnal_rozbieznosci (różnica ≥ 20 pp), brak_sygnalu albo za_malo_danych (mniej niż 20 oznaczonych orzeczeń po którejś stronie); flaga nie jest testem istotności, obok podany z_roznicy (test dwóch proporcji). Przykłady: najczęściej cytowane oznaczone orzeczenie każdego kubełka po stronie SN i SA/SO (sygnatura, sąd, data, URL, cytowane_n) oraz uchwały SN z próbki. Ten sam algorytm co test rozbieżności asystenta Prawnet. Oznaczone wyniki SN kończą się w połowie 2016 r.; to sygnał do sprawdzenia, nie stwierdzenie rozbieżności.

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": "rozbieznosc_orzecznicza"
  }
}

Input Schema

NameRequiredDescriptionDefault
pNoBez przepis: POZYCJA w Dz.U., nie numer (k.c. 1964/93)
yNoBez przepis: rok Dz.U.
artNoBez przepis: nr artykułu ("385-1" = 385¹), do 16 znaków
przepisNoCytat ("art. 446 § 4 kc", "art. 5 ustawy o prawach konsumenta") albo potoczna nazwa ("zasiedzenie"); zamiast y, p, art. Do 160 znaków

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Although the annotations already establish readOnlyHint and idempotency, the description adds substantial behavioral context that the annotations do not provide: the sample-size floor of 20 labelled rulings, the 20-percentage-point flag threshold, an explicit statement that the flag is not a significance test, and the major data limitation that labelled SN results stop in mid-2016. It also warns that the output is a signal for checking, not a finding of divergence. That is strong disclosure for a read-only tool.

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?

Despite its density, the content is front-loaded: it identifies the tool as a statistical divergence signal, then the flag semantics, then the sample output. Every clause carries information, although the single run-on paragraph and the overlapping caveats ('flaga nie jest testem istotności' and the closing 'to sygnał do sprawdzenia') make it harder to scan than it needs to be.

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?

The tool is moderately complex, and the description covers output content, thresholds, a statistical caveat and a data-coverage limit; it also has the benefit of a full output schema, so it need not spell out return values. The main gap is the missing routing guidance against similar siblings, and the description does not clarify how przepis relates to y/p/art beyond what the schema already says.

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 the schema already explains p (Dz.U. position, not number), y (year), art (article number with the 385-1 notation) and przepis (citation or colloquial name, used instead of y/p/art). The description only says 'do artykułu' and adds no further meaning about how these four inputs interact, so the 3 baseline applies.

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 states a specific computation: the distribution of ruling outcomes in a sample of rulings citing a given article, broken down by court level, plus a comparison of grant rates between SN and SA+SO. The object and operation are unambiguous, but the description never distinguishes this tool from the similar sibling jak_orzekaja_sady, which likely also profiles rulings by article.

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?

The usage context comes through implicitly: this is a per-article statistical divergence check, and the thresholds (fewer than 20 labelled rulings produces za_malo_danych) indicate when the tool is usable at all. It never states when to pick this tool instead of siblings such as jak_orzekaja_sady, wynik_orzeczenia or trend_przepisu, so the agent must infer which tool fits.

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