Skip to main content
Glama

Prawnet: Polish case law and legislation

Profil procesowy podmiotu

profil_procesowy
Read-onlyIdempotent

Profil procesowy osoby prawnej lub instytucji publicznej w opublikowanych orzeczeniach bazy Prawnet: liczba orzeczeń z jej udziałem, role (powód / pozwany), rozkład rozstrzygnięć I instancji wg roli (etykiety o wysokiej pewności, przedziały Wilsona 95%), kategorie spraw, lata i 5 najnowszych orzeczeń z linkami. Zakres: sprawy z art. 385¹ k.c. (kredyty walutowe, inne klauzule niedozwolone) i art. 444–446 k.c. (szkoda na osobie). SAOS i SN anonimizują nazwy spółek, więc rozpoznawane są tylko podmioty, których nazwa zostaje w tekście (Skarb Państwa, UFG, PZU, PZU Życie, ZUS, KRUS, NFZ), oraz grupy (banki, ubezpieczyciele, szpitale, samorządy); pojedynczego banku nie da się wskazać (status nie_rozpoznano). Osoby fizyczne: status niedozwolone, bez danych. Liczby obejmują tylko opublikowane orzeczenia (bez ugód i cofniętych pozwów) i nie są szansą wygranej. Bez nazwisk i treści orzeczeń.

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": {
      "podmiot": "<podmiot>"
    },
    "name": "profil_procesowy"
  }
}

Input Schema

NameRequiredDescriptionDefault
podmiotYesNazwa, NIP lub KRS osoby prawnej / instytucji ("Skarb Państwa", "UFG", "KRS 0000009831") albo grupa ("banki", "ubezpieczyciele", "szpitale", "gminy"). Do 120 znaków
kategoriaNokredyt_walutowy, klauzule_konsumenckie (art. 385¹ k.c.), szkoda_osobowa (art. 444–446 k.c.)

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses the anonymization constraints of SAOS and SN, the recognition statuses ('nie_rozpoznano', 'niedozwolone'), that counts cover only published rulings without settlements or withdrawn claims, and that the figures are not a win probability. It also states the output deliberately omits names and ruling text — rich behavioral context that annotations cannot convey.

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?

Every sentence carries substantive information — there is little true waste — but the whole definition is a single dense block in which the critical scope restriction (only art. 385¹ and 444–446 cases, individuals disallowed) is buried mid-paragraph rather than front-loaded. Structural separation would make scanning far easier.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a two-parameter tool with an output schema and full annotation coverage, the description is complete: it defines the data universe, the recognition limits, the interpretive caveats, and even the meaning of low-confidence outcome labels. An agent can decide whether to call it and interpret the result without further context.

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 adds real meaning: it lists the concrete entity forms that resolve ('Skarb Państwa', 'UFG', 'PZU', 'ZUS', 'KRUS', 'NFZ') and the accepted groups (banks, insurers, hospitals, municipalities), while warning that an individual bank yields 'nie_rozpoznano'. That materially guides how to populate 'podmiot'.

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 specific resource — a litigation profile of a legal entity drawn from published Prawnet rulings — and enumerates exactly what the profile contains: ruling counts, party roles, first-instance outcome distribution with Wilson intervals, case categories, years, and five recent rulings with links. It is not tautological and clearly differs from a ruling-search or provision tool, though it never explicitly names a sibling to route away from.

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?

It states the operative scope precisely: only cases under art. 385¹ k.c. and art. 444–446 k.c., only entities whose names survive anonymization, and 'niedozwolone' for natural persons. Those are strong when-not conditions, but no alternative tool is named for the cases this tool cannot handle (individuals, a single unnamed bank), so the agent must infer the fallback.

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