Skip to main content
Glama

Prawnet: Polish case law and legislation

Wiodące orzeczenia do przepisu

wiodace_orzeczenia
Read-onlyIdempotent

Orzeczenia o najwyższym autorytecie cytowaniowym (PageRank w grafie orzeczenie → orzeczenie) spośród powołujących dany artykuł (jak REST /v1/przepisy/{y}/{p}/{art}/wiodace): wiodące orzecznictwo do art. X, ranking wg autorytetu, nie daty. Z każdym: cytowane_n, poziom autorytetu i los (uchylone/utrzymane, gdy znany). „Wiodące" = pomiar w naszym grafie, nie ocena doktryny. Dla przepisu cytowanego rutynowo (koszty, procedura — np. art. 98 k.p.c.) pole uwaga mówi, że autorytet pozycji pochodzi z innych zagadnień, a nie z tego przepisu.

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": {
      "y": "<y>",
      "p": "<p>",
      "art": "<art>"
    },
    "name": "wiodace_orzeczenia"
  }
}

Input Schema

NameRequiredDescriptionDefault
pYesPOZYCJA w Dz.U. (nie numer): k.c. 1964/93, k.p.c. 1964/296, k.k. 1997/553, k.p.k. 1997/555, k.p. 1974/141, k.r.o. 1964/59, k.s.h. 2000/1037, k.p.a. 1960/168, Pzp 2019/2019
yYesRok Dz.U. (np. 1997 dla k.k.)
artYesNumer artykułu: "415", "178a", "385-1" (indeks górny jako -N); do 16 znaków
sadNoOpcjonalny filtr rodzaju sądu (ADMINISTRATIVE = NSA/WSA — tylko wybór orzeczeń)
limitNoIle orzeczeń (1–20); pominięte = 10

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / art / description
      Previous value: -"Numer artykułu w formie URL: \"178a\", \"415\", \"385-1\" (indeks górny jako -N); do 16 znaków"New value: +"Numer artykułu: \"415\", \"178a\", \"385-1\" (indeks górny jako -N); do 16 znaków"
    • changedInput schema / properties / p / description
      Previous value: -"Pozycja w Dzienniku Ustaw (y/p): k.c. 1964/93, k.p.c. 1964/296, k.k. 1997/553, k.p.k. 1997/555, k.p. 1974/141, k.r.o. 1964/59, k.s.h. 2000/1037, k.p.a. 1960/168, Pzp 2019/2019 — POZYCJA, nie numer Dz.U."New value: +"POZYCJA w Dz.U. (nie numer): k.c. 1964/93, k.p.c. 1964/296, k.k. 1997/553, k.p.k. 1997/555, k.p. 1974/141, k.r.o. 1964/59, k.s.h. 2000/1037, k.p.a. 1960/168, Pzp 2019/2019"
    • changedInput schema / properties / y / description
      Previous value: -"Rok Dziennika Ustaw (np. 1997 dla Kodeksu karnego)"New value: +"Rok Dz.U. (np. 1997 dla k.k.)"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "citations": {
      +      "type": "array"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "wersja_danych": {
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile needs no restating. The description does add real value beyond that: the ranking mechanism, the per-ruling payload (cytowane_n, poziom autorytetu, los uchylone/utrzymane), and the `uwaga` self-qualification for routinely cited provisions. It stops short of richer behavior (how ties are broken, how `los` is determined when unknown), which keeps it at solid-but-not-rich.

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 core claim and the ranking rationale, then the caveat, then the edge-case field. Dense but every clause carries meaning; the heavy parentheticals and the trailing art. 98 k.p.c. example make it slightly harder to scan than ideal.

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?

An output schema exists, so return-shape explanation is largely unnecessary, and the description still usefully names the key returned attributes and the `uwaga` caveat. For a 5-parameter, read-only analytical query this is close to complete; only the absence of explicit alternative-routing and tie-breaking detail leaves a minor gap.

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%, with per-parameter guidance already in the schema (e.g. POZYCJA not numer, superscript notation '-N', sad enum semantics, limit default 10). The description adds no parameter-level information beyond the schema, so the baseline 3 applies.

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?

Names a specific resource and scope — 'Orzeczenia o najwyższym autorytecie cytowaniowym ... spośród powołujących dany artykuł' — plus the ranking criterion (PageRank over the orzeczenie→orzeczenie graph). This clearly distinguishes it from a plain 'rulings citing article' lookup or a full-text search, and the REST equivalent is given for anchoring.

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?

The semantics of 'wiodące' are explicitly bounded ('pomiar w naszym grafie, nie ocena doktryny'), which guides when the answer is a proxy rather than a doctrinal judgment. It also flags routine-article cases (e.g. art. 98 k.p.c.) where the `uwaga` field applies. It does not explicitly steer between alternatives such as orzeczenia_do_przepisu or szukaj_orzeczen, so no exclusions are stated.

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