Skip to main content
Glama

Prawnet: Polish case law and legislation

Wyszukiwanie w treści orzeczeń

szukaj_orzeczen
Read-onlyIdempotent

Wyszukiwanie pełnotekstowe w orzeczeniach z bazy Prawnet (SAOS: sądy powszechne i SN do 06.2016; repozytorium SN od 06.2016; KIO; TK; NSA/WSA z CBOSA). Składnia: wszystkie słowa muszą wystąpić; OR łączy warianty; tekst w cudzysłowie = słowa w tej kolejności; minus wyklucza słowo lub frazę. Dopasowanie wpisanej formy wyrazu (bez lematyzacji; wielkość liter bez znaczenia, polskie znaki istotne); formy odmiany łączy OR. Filtry: rodzaj sądu, lata. Strona = najnowsze trafienia, w obrębie strony wg autorytetu (PageRank). Trafienia tylko w nagłówku lub podpisach (sąd, skład) pomijane, chyba że fraza to sygnatura. sad = ADMINISTRATIVE: indeks NSA/WSA (teza, sentencja, hasła, części uzasadnienia; bez kolejności słów). Wynik: id, sygnatura, sąd, data, rodzaj, URL, fragment z trafieniem (do 300 znaków), cytowane_n, autorytet_percentyl, źródło; razem = dokładna liczba albo null (frazy bardzo częste; cytaty z ponad 800 kandydatami). Bez nazwisk sędziów i pełnych tekstów.

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": {
      "fraza": "<fraza>"
    },
    "name": "szukaj_orzeczen"
  }
}

Input Schema

NameRequiredDescriptionDefault
sadNoRodzaj sądu (ADMINISTRATIVE = NSA/WSA)
frazaYesSłowa ("umowa OR umowy OR umowie"; "słowa w kolejności"; -słowo, -"fraza" wyklucza); bez odmiany, ą ≠ a. Do 200 znaków
limitNoDomyślnie 10
offsetNoNastępna strona: strona.nastepny_offset
rok_doNoNajpóźniejszy rok (włącznie)
rok_odNoNajwcześniejszy rok (włącznie)

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: -"Rodzaj sądu (ADMINISTRATIVE = wybór NSA/WSA)"New value: +"Rodzaj sądu (ADMINISTRATIVE = NSA/WSA)"
  2. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's added value is elsewhere and it delivers: result ordering (newest first, then PageRank authority within a page), the rule that header/signature-only matches are skipped unless the phrase is a case citation, the absence of judge names and full texts, and the caveat that "razem" is null for very frequent phrases (>800 candidates). It loses a point because part of the text is spent enumerating return fields that the output schema already supplies.

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?

The lead is well front-loaded with purpose and source coverage, but the rest is one dense semicolon-and-parenthesis block with no visual segmentation. Several clauses repeat what the fraza schema description and the output schema already state (quote/minus syntax, the return field list), so not every sentence adds new information.

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 full-text search tool with an output schema and full annotation coverage, this is nearly complete: sources, ranking, exclusions, count reliability, and the special ADMINISTRATIVE index are all addressed. The remaining gap is selection guidance against sibling search tools, which an agent would still have to infer.

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%, so baseline is 3, but the description earns above that: it explains matching behavior not in the schema (no lemmatization, exact inflected form must be entered, case-insensitive yet Polish diacritics are significant, OR joins inflection variants) and clarifies that sad=ADMINISTRATIVE uses a different NSA/WSA index with no word-order constraint. Filter and pagination semantics (rodzaj sądu, lata, strona) are echoed from the schema rather than extended.

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?

Opens with a specific verb+resource ("Wyszukiwanie pełnotekstowe w orzeczeniach") and immediately pins the scope to concrete databases and coverage windows (SAOS sądy powszechne i SN do 06.2016, repozytorium SN od 06.2016, KIO, TK, NSA/WSA z CBOSA). That coverage detail alone separates it from act-level siblings such as szukaj_aktow or tresc_przepisu without needing to name them.

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 is implied by the scope: use it when searching ruling text by words or phrases. However, there is no explicit when-not and no routing to the obvious alternatives (orzeczenia_do_przepisu for provision-linked lookups, sprawdz_sygnature for citation lookups, cytowania_orzeczenia for citation graphs). The syntax section is query mechanics, not tool selection guidance.

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