Skip to main content
Glama

Prawnet: Polish case law and legislation

Rejestr Halucynacji

rejestr_halucynacji
Read-onlyIdempotent

Rejestr Halucynacji Prawnet (dane jak prawnet.pl/halucynacje): sygnatury, o które pytano weryfikator, a których według mocnego kryterium nie ma w publicznych rejestrach — kandydaci na sygnatury zmyślone przez asystentów AI. Pozycja jest na liście, gdy pytano o nią w co najmniej 3 różnych dniach w oknie 180 dni, a aktualny weryfikator nadal odpowiada „brak”. Tylko rejestry, które mamy w całości: TK i KIO w rocznikach o pełnym pokryciu — nigdy SN ani sądy powszechne. Dla każdej sygnatury: liczba zapytań i dni, pierwszy i ostatni dzień, podział wg klasy klienta (deklaracja nagłówka: ChatGPT, Perplexity, Claude, inne). Podsumowanie okna i metodologia. Bez adresów IP, treści rozmów i tożsamości pytających; wywołania z kluczem API nie są liczone. Lista bywa pusta, gdy żadna sygnatura nie spełnia progu.

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": "rejestr_halucynacji"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDomyślnie 20; liczba_pozycji = długość całej listy

Output Schema

NameRequiredDescriptionDefault
statusNo
citationsNo
wersja_danychNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses substantive behavior: privacy guarantees (no IPs, no conversation contents, no requester identities), that API-key calls are excluded from counts, that the list can legitimately be empty, and the exact registry coverage limits. These are exactly the caveats an agent needs to interpret an empty or partial result.

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 what the tool is, then criteria, coverage, per-item fields, and privacy limits — a sensible order. It is a single dense paragraph with some redundancy (e.g. 'mocne kryterium' restated as the 3-day rule), but nearly every clause carries real 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 criteria-driven listing tool with an output schema and full safety annotations, the description covers scope, thresholds, exclusions, per-item statistics, privacy boundaries, and empty-result behavior. The one gap is how the returned list relates to the 'limit' parameter (total vs. truncated), which the description leaves to the schema.

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?

There is only one parameter and the schema documents it fully (default 20, max 50, and that item count equals total list length), so the 100% coverage baseline applies. The description adds nothing about the limit or about truncation of the overall list, so it neither compensates nor harms.

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 states a concrete resource with precise semantics: a registry of case signatures that were queried but are absent from fully covered public registries — candidates for AI-fabricated citations. It also defines the inclusion rule (asked on at least 3 distinct days within a 180-day window and still 'brak'). It never contrasts itself with the obvious sibling sprawdz_sygnature (single-signature check), so an agent must infer the routing.

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 conveyed indirectly through the inclusion threshold, the coverage restriction ('only TK and KIO, never SN or common courts'), and the warning that the list may be empty. There is no explicit 'use this when X, use sprawdz_sygnature when Y' guidance, so the agent has to derive the selection rule itself.

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