Skip to main content
Glama

Fr Judilibre Search

fr_judilibre_search
Read-onlyIdempotent

Search French judicial decisions (Cour de cassation and the courts of appeal it indexes) published as open data: full-text query plus filters for jurisdiction, chamber, formation, decision type, theme, publication level and solution, paged. Returns decision ids, summaries and highlighted snippets; fr_judilibre_decision reads the full text. Codes like "cc" (jurisdiction) or "civ1" (chamber) resolve to French labels via fr_judilibre_taxonomy.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "responsabilité du fait des choses",
      "page_size": 3,
      "jurisdiction": [
        "cc"
      ]
    },
    "name": "fr_judilibre_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo0-based page number (default 0).
typeNoDecision type codes, e.g. "arret" (judgment), "qpc" (constitutionality question). See fr_judilibre_taxonomy(id:"type").
fieldNoRestrict the full-text match to these decision zones, e.g. ["motivations","dispositif"]. Omit to search the whole decision.
queryNoFull-text search terms, e.g. "responsabilité du fait des choses".
themeNoSubject-matter theme codes. See fr_judilibre_taxonomy(id:"theme").
chamberNoChamber codes, e.g. "civ1", "soc", "comm", "crim". See fr_judilibre_taxonomy(id:"chamber").
date_endNoDecision date range end, ISO YYYY-MM-DD.
solutionNoOutcome codes, e.g. "rejet", "cassation". See fr_judilibre_taxonomy(id:"solution").
formationNoFormation codes (bench size/type). See fr_judilibre_taxonomy(id:"formation").
page_sizeNoResults per page, 1-50 (default 10).
date_startNoDecision date range start, ISO YYYY-MM-DD.
publicationNoPublication-level codes, e.g. "b" (Bulletin), "r" (Rapport). See fr_judilibre_taxonomy(id:"publication"). A decision with none of these is unpublished, most are.
jurisdictionNoJurisdiction codes, e.g. "cc" (Cour de cassation), "ca" (cour d'appel). See fr_judilibre_taxonomy(id:"jurisdiction").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / publication / description
      Previous value: -"Publication-level codes, e.g. \"b\" (Bulletin), \"r\" (Rapport). See fr_judilibre_taxonomy(id:\"publication\"). A decision with none of these is unpublished — most are."New value: +"Publication-level codes, e.g. \"b\" (Bulletin), \"r\" (Rapport). See fr_judilibre_taxonomy(id:\"publication\"). A decision with none of these is unpublished, most are."
  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, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing what comes back (decision ids, summaries, highlighted snippets) and that results are paged, which is not derivable from the annotations and matters because there is no output schema.

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?

Two dense sentences, front-loaded with the core verb and scope, then returns and routing. Nothing is padding, though the second sentence packs returns, paging, a sibling pointer and a taxonomy note together, which slightly dilutes scanability.

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 13-parameter, zero-required search tool with no output schema, the description covers the essential elements: what is searched, what filters exist, what is returned, and how to decode codes. Only a note on result limits or the meaning of highlighted snippets is missing.

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?

Schema description coverage is 100%, so the schema already explains every parameter, including examples and default values. The description only groups the filters into a list and echoes the taxonomy-resolution hint that the schema itself already repeats; it adds no syntax, combination rules, or format details beyond that. Baseline 3 is appropriate.

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 ('Search French judicial decisions') with the exact jurisdictional scope (Cour de cassation and indexed courts of appeal) and open-data provenance. It also distinguishes itself from fr_judilibre_decision by limiting itself to ids, summaries and snippets, so an agent can tell the two apart 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?

Explicitly routes two follow-up needs: fr_judilibre_decision for full text and fr_judilibre_taxonomy for resolving codes like "cc" or "civ1". It gives clear context for when to use it, but offers no exclusions or guidance on when a different search tool (e.g. search_within) would be preferable.

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.