Skip to main content
Glama

Prawnet: Polish case law and legislation

Procedura krok po kroku

procedura
Read-onlyIdempotent

Procedura prawna krok po kroku z biblioteki Prawnet (31 procedur, m.in. rozwód, alimenty, spadek, pozew o zapłatę, sprzeciw od nakazu zapłaty, egzekucja komornicza, eksmisja, odwołanie od wypowiedzenia, skarga do WSA, reklamacja). Wejście: slug albo fraza (słowa tematu); bez obu — lista procedur. Zwraca kroki (kto, gdzie, termin z podstawą prawną, dokumenty z linkiem do wzoru, ryzyka, wskazówka, rozgałęzienia tak/nie), koszty, czas trwania, pytania FAQ (odpowiedzi z faq: true), do 15 przepisów najczęściej powołanych w krokach (link do artykułu, liczba orzeczeń bazy powołujących artykuł), powiązane wzory, kalkulatory i procedury, datę stanu prawnego. sytuacja (opis własnymi słowami): do 5 pasujących procedur z uzasadnieniem, dopasowanie po słowach. lista_kontrolna: true: kroki, terminy, dokumenty i koszty jako uporządkowana lista. Treść redakcyjna sprawdzona z tekstami jednolitymi ustaw; informacja ogólna, nie porada prawna.

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": "procedura"
  }
}

Input Schema

NameRequiredDescriptionDefault
faqNotrue = także odpowiedzi FAQ (domyślnie same pytania, faq_pytania)
slugNoProcedura, np. "rozwod", "sprzeciw-od-nakazu-zaplaty", "odwolanie-od-decyzji-zus" (lista: wynik bez slug i fraza); nieznany slug działa jak fraza
frazaNoTemat słowami ("nakaz zapłaty", "komornik"); dopasowanie po słowach tytułu, opisu i kroków (odmiana po rdzeniu). Do 200 znaków
jezykNopl (domyślnie) albo en (te same treści po angielsku; przepisy w polskiej formie cytatu)
sytuacjaNoOpis sytuacji zwykłymi słowami ("mąż odszedł, mamy dwoje dzieci, chcę rozwodu"); zwraca pasujące procedury z uzasadnieniem. Do 500 znaków; slug lub fraza mają pierwszeństwo
lista_kontrolnaNotrue (ze slug lub fraza) = zamiast pełnej procedury uporządkowana lista kontrolna: kroki, terminy, dokumenty, koszty

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / lista_kontrolna
      Added value: +{
      +  "description": "true (ze slug lub fraza) = zamiast pełnej procedury uporządkowana lista kontrolna: kroki, terminy, dokumenty, koszty",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / sytuacja
      Added value: +{
      +  "description": "Opis sytuacji zwykłymi słowami (\"mąż odszedł, mamy dwoje dzieci, chcę rozwodu\"); zwraca pasujące procedury z uzasadnieniem. Do 500 znaków; slug lub fraza mają pierwszeństwo",
      +  "type": "string"
      +}
  2. Added

TDQS

A3.6/5.0
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 safety profile is covered. The description still adds real context the annotations cannot: content is editorial and verified against consolidated statute texts, the legal-state date is returned, and it explicitly frames output as general information rather than legal advice. No gaps that would mislead an agent.

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

Conciseness2/5

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

The purpose is front-loaded in the first clause, but the body is one dense run-on of semicolon-joined clauses with a long parenthetical enumeration of procedure topics and another listing returned fields. Much of that enumeration duplicates the output schema or the parameter descriptions, so the length is not earning its place. It is informative but poorly structured and over-long.

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 six-parameter tool with a full output schema, the description covers the modes, their precedence, the language option and the legal disclaimer, which is what an agent needs before calling. It arguably over-explains return contents that the output schema already provides. Nothing essential for correct invocation is missing.

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 coverage is 100% and every parameter, including enum values for jezyk and length limits, is already documented in the schema. The description restates each parameter's role and adds the interplay between slug, fraza and sytuacja, but most of that interplay is also visible in the schema descriptions. It adds marginal meaning rather than new semantics, so the 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 names a concrete resource (a step-by-step legal procedure from the Prawnet library of 31 procedures) and enumerates what a result contains: steps, costs, duration, FAQ, most-cited provisions, related templates and calculators, and the legal-state date. That is far more specific than the bare name. It does not, however, differentiate itself from overlapping siblings such as ile_trwa_sprawa, koszty_zastepstwa or przepisy_powiazane, whose subject matter it also returns as fields.

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 input modes are spelled out: a slug or a phrase selects a procedure, neither of them returns the procedure list, and a free-text situation returns up to five matched procedures with justification. Precedence is stated explicitly ("slug lub fraza mają pierwszeństwo"), which is genuine routing guidance. What is missing is when to prefer this tool over its siblings or when not to use it at all.

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