Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

juris_decision

A French or European court decision (jurisprudence) — search the collections full text, or read one decision in full.

op:

  • "search" (default): search French & European case law (jurisprudence) full text — how courts actually ruled. Unified collections, ranked by FTS relevance × court authority, with legal-thesaurus query expansion. Returns {count, decisions: [{id, titre, juridiction, date_dec, solution, extrait, source_url, …}]}. Full text via op="get".

  • "get": full text of a French court decision, with metadata (juridiction, formation, solution, ECLI) and a verifiable Légifrance source_url.

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": "juris_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNosearch (default) | get.search
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
fondNoop="search" — restrict to one collection — "cass" (Cour de cassation, published) | "inca" (cassation, unpublished) | "capp" (cours d'appel) | "jade" (administrative DILA: CE/CAA/TA) | "jade_live" (administrative, portail live) | "constit" (Conseil constitutionnel) | "cnil" | "cedh" (Cour EDH) | "cjue" (CJUE/Tribunal UE) | "judilibre" (Cass/CA/TJ live).
limitNoop="search" — max results (default 20, max 50).
queryNoop="search" — full-text query (websearch syntax, french stemming), ex "requalification CDD d'usage intermittent".
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
expandNoop="search" — legal-thesaurus synonym expansion (default True — set False for strict literal matching).
_run_idNoOBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
date_maxNo
date_minNo
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
decision_idNoop="get" — id returned by op="search" (JURITEXT…, CETATEXT…, CONSTEXT…, CNILTEXT…).
juridictionNoop="search" — court name filter (ILIKE), ex "cassation", "appel de Paris", "Conseil d'État".

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the ranking model (FTS relevance × court authority), thesaurus query expansion as a default, the response shape for search, and that get returns metadata plus a verifiable Légifrance source_url. It omits any statement about access restrictions, rate limits, or mutability (implicitly read-only), leaving a small gap.

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?

The definition is front-loaded with a one-line purpose followed by a tightly structured per-operation breakdown, and each bullet earns its place. It runs slightly long for the amount of new information conveyed, but nothing is genuinely redundant.

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

Completeness3/5

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

For a 14-parameter tool with no annotations and no output schema, the description helpfully supplies return shapes for both ops. However, it is silent on the mandatory _run_id note and the tenancy parameters that make up a large share of the schema, leaving an agent without guidance on invocation context.

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 coverage is 86%, so the schema already documents op, fond collections, limit, query, expand, and decision_id; the description adds chiefly the connection between op='get' and search-returned ids. The tenancy parameters (_org, _group, _project, _instance, _run_id) are not addressed at all, and date_min/date_max have no description anywhere, so the description does not fully compensate.

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 description names the resource precisely ("French or European court decision (jurisprudence)") and splits it into two concrete operations, search and get, so an agent knows exactly what the tool retrieves. It also contrasts case law ("how courts actually ruled") with what it is not, distinguishing it from statute-oriented siblings like loi_article or ccn_article.

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?

Usage is explicit for the two modes: search is the default for full-text case-law queries, and "Full text via op='get'" tells the agent to switch modes to read a specific decision. There are no explicit exclusions or named alternative tools for cases where a different legal source is more appropriate, which keeps it short of a 5.

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

All Tulina toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources