Skip to main content
Glama

Search Swiss court decisions

search_court_decisions
Read-only

Search Swiss federal and cantonal court decisions by keyword, legal provision, or docket number, and filter results by court, canton, and date to locate relevant rulings.

Instructions

Full-text search across Swiss court decisions aggregated by entscheidsuche.ch: Federal Supreme Court (BGer/BGE), Federal Administrative Court (BVGer), Federal Criminal Court (BStGer), Federal Patent Court and the courts of all 26 cantons. Returns docket/reference number, decision date, court, canton, title, abstract snippet, matching text excerpts and a link to the decision (PDF/HTML). Query syntax: words are AND-ed; use "quotes" for phrases, | for OR, - to exclude. Examples: query='Mietzins Kündigung' canton='ZH'; query='"Art. 336 OR"' court='BGer' date_from='2020'; query='5A_123/2020'.

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": {
      "query": "<query>"
    },
    "name": "search_court_decisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance
courtNoCourt: 'BGer', 'BGE', 'BVGer', 'BStGer', 'BPatGer', or an index code like 'ZH_OG' / 'CH_BGer'
limitNo
queryYesSearch terms, a legal provision or a docket number
cantonNoCanton code, e.g. 'ZH'; 'CH' = federal courts
date_toNoLatest decision date
languageNoPreferred language for titles/abstracts (boosted, not filtered)
date_fromNoEarliest decision date, e.g. '2020' or '2020-01-31'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds provenance (aggregated by entscheidsuche.ch across federal and cantonal courts) and the full result shape. It does not mention result capping, ranking behaviour, or whether the backend imposes rate limits, which are the remaining behavioural unknowns for a federated search.

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?

Well front-loaded: corpus, then return payload, then query syntax with examples. The opening sentence is long and heavily parenthetical with court acronyms, but no sentence is filler and the closing example block is densely informative rather than redundant.

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?

There is no output schema, and the description compensates by listing the returned fields, and it documents the unconventional query language that no structured field captures. The gap is result-set mechanics: nothing says results are capped at 20, how sorting between relevance and date behaves in practice, or that no pagination parameter exists.

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 75% schema coverage the schema already documents most fields, but the description supplies the query grammar the schema omits entirely: AND-by-default, quoted phrases, '|' for OR, '-' for exclusion, plus docket-number search. The examples further show how court, canton and date_from compose. Sort, limit and date semantics are still left to the schema, so it is additive rather than complete.

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?

States a specific verb and resource ('Full-text search across Swiss court decisions') and scopes the corpus precisely by naming the aggregator (entscheidsuche.ch) and every court family covered, including all 26 cantons. It also enumerates what comes back (docket number, date, court, canton, title, snippet, excerpts, link), so an agent can distinguish it from retrieval-style siblings without opening a schema.

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?

Three worked examples make the intended call patterns concrete: keyword search narrowed by canton, a citation-and-court-and-date query, and a bare docket lookup, which implicitly tells the agent this tool also handles reference-number searches. There is no explicit statement of when not to use it or which sibling to prefer for a known docket number, so the guidance stops short of full routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools