Skip to main content
Glama

justicelibre

by io.github.Dahliyaal
OverviewDiscussionsAdmin

get_law_article

Read-only

Renvoie le texte d'un article de loi à une date donnée (ou version actuelle si date vide).

Particularité justicelibre : quand une décision de 1992 cite
l'article 1128 du Code civil, l'article a été totalement réécrit en
2016. Avec ce tool on récupère le texte **tel qu'il existait en 1992**
(l'ancienne version napoléonienne), pas le texte actuel.

Codes/textes supportés : ~80 sigles courts — les grands codes (CC, CP,
CPC, CPP, CT, CSP, CJA, CRPA, CSS, COJ, CGFP, LPF, CSI, CSport…), la
Constitution (CONST) et des lois non codifiées (LIL, LO58, L2005-102).
Liste complète : resource `justicelibre://codes-supportes`. Pour tout
autre texte (loi, ordonnance, décret), passer un identifiant
LEGITEXT/JORFTEXT direct — `resolve_law_number()` le trouve depuis un
numéro ("78-17" → JORFTEXT…).

Args:
    code: code court (ex : "CC" pour Code civil, "CT" pour Code du travail)
    num: numéro de l'article (ex : "1128", "L1152-1", "132-1")
    date: date ISO YYYY-MM-DD (optionnel — si absent, version en vigueur).
          Utiliser la date de la décision citante pour obtenir la
          version contemporaine de la citation.

Returns:
    dict avec `legiarti`, `num`, `code`, `titre_texte`, `texte`, `etat`
    (VIGUEUR/MODIFIE/ABROGE), `date_debut`, `date_fin`, `nota`. Plus
    un champ `note` si la version retournée n'est pas celle demandée.

    `titre_texte` est le titre du TEXTE parent (« Code civil ») ;
    `titre_section` est le dernier niveau du plan du code (« Chapitre Ier :
    La responsabilité extracontractuelle en général »), servi depuis la
    ré-ingestion du 10 septembre 2026 (colonne `hierarchie`) et mesuré
    juste sur 30 articles de 30 codes le 13 septembre 2026. Le plan
    complet (partie / livre / titre / chapitre / section) n'est pas encore
    servi : ne pas l'inventer, renvoyer vers Légifrance s'il est demandé.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
numYes
codeYes
dateNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the date-versioning behavior, the `note` field when the returned version differs from the requested one, and a candid limitation (only `titre_section` is served, the full plan is not, don't invent it). This is exactly the extra context annotations cannot carry.

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 and the key date-versioning quirk are front-loaded and every section earns its place overall, but the titre_section paragraph carries ingestion-benchmark trivia ("ré-ingestion du 10 septembre 2026", "mesuré juste sur 30 articles de 30 codes le 13 septembre 2026") that is noise for an agent. Slightly long but not padded.

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

Completeness5/5

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

For a 3-parameter lookup tool with a real output schema, the description covers supported inputs, the alternative path for unsupported texts, version-selection semantics, and known return limitations. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load and does: it defines `code` (short sigle, e.g. CC/CT), `num` with concrete formats ("1128", "L1152-1", "132-1"), and `date` as optional ISO YYYY-MM-DD with a clear default behavior when empty.

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 — returns the text of a law article at a given date (or the current version) — and immediately distinguishes itself from get_law_versions via the 1992/Code civil example. An agent can tell exactly what it gets back without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use context (pass the citing decision's date to get the contemporaneous version), names an alternative route for texts outside the ~80 supported codes (LEGITEXT/JORFTEXT direct, found via resolve_law_number()), and points to the justicelibre://codes-supportes resource for the supported list. Routing is unambiguous.

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

All justicelibre 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