Skip to main content
Glama

Prawnet: Polish case law and legislation

Ile zasądzają sądy (Barometr)

ile_zasadzaja
Read-onlyIdempotent

Rozkład kwot zasądzanych przez polskie sądy I instancji dla typu roszczenia (zadośćuczynienie, odszkodowanie). Nagłówek ostatnie_lata: mediana OSOBNO dla sądu rejonowego i okręgowego z wyroków ostatnich 5 lat — właściwy szczebel zależy od wartości sprawy (progi i wyjątki: szczeble_wlasciwosc w wyniku). Niżej wszystkie lata, segmenty wg podstawy (zadośćuczynienie: art. 445 / 446 / 448 k.c.; odszkodowanie: spory z ubezpieczycielem / inne) i rozkład rozstrzygnięć I instancji. To ROZKŁAD HISTORYCZNY na oznaczonej próbce korpusu, nie prognoza i nie ocena sprawy; każda liczba ma n, szczebel i okres. Kwoty nominalne w PLN.

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": {
      "roszczenie": "<roszczenie>"
    },
    "name": "ile_zasadzaja"
  }
}

Input Schema

NameRequiredDescriptionDefault
roszczenieYeszadoscuczynienie (krzywda niemajątkowa, art. 445, 446 § 4, 448 k.c.) albo odszkodowanie (szkoda majątkowa)

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / roszczenie / description
      Previous value: -"Typ roszczenia: \"zadoscuczynienie\" (krzywda niemajątkowa, art. 445, 446 § 4, 448 k.c.) albo \"odszkodowanie\" (szkoda majątkowa)"New value: +"zadoscuczynienie (krzywda niemajątkowa, art. 445, 446 § 4, 448 k.c.) albo odszkodowanie (szkoda majątkowa)"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "citations": {
      +      "type": "array"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "wersja_danych": {
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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 is covered. The description adds real behavioral context beyond that: the data is a historical distribution over a marked corpus sample, every figure carries n, tier and period, and amounts are nominal PLN. It does not discuss response size or limits, but the caveats it does give are substantive.

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?

Purpose is front-loaded in the first clause and every subsequent sentence adds non-redundant information (tier logic, segmentation, distribution of rulings, historical-sample caveat). The single dense paragraph with heavy jargon is harder to scan than a short bulleted structure would be, but no sentence is filler.

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 values need not be spelled out, yet the description goes further and explains the header block (ostatnie_lata, medians separately for rejonowy and okręgowy) and the lower sections. Combined with the sample/provenance caveat, this is close to complete for a read-only single-enum query tool.

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?

With a single parameter at 100% schema coverage, the schema already carries the enum and its legal anchors. The description still adds meaning by mapping each enum value to how results are segmented (zadośćuczynienie by art. 445/446/448, odszkodowanie by insurer-dispute vs. other), which tells the agent what each choice will actually produce.

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?

The opening clause names a specific resource and measurement: the distribution of amounts awarded by Polish first-instance courts, split by claim type (zadośćuczynienie, odszkodowanie). It also delimits itself negatively ("nie prognoza i nie ocena sprawy"), which separates it from judgment-quality or case-assessment siblings despite no sibling being named explicitly.

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 rather than stated: the description explains that the correct court tier depends on the case value and points to szczeble_wlasciwosc in the result, and it warns the figures are not a forecast. There is no explicit routing to alternatives (e.g. jak_orzekaja_sady for ruling patterns vs. this tool for awarded amounts), so the agent must infer when to pick this tool.

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