Citexact : jurisprudence administrative française

Rechercher Texte

rechercher_texte

Read-onlyIdempotent

Textes issus de Légifrance (LEGI) : fonction publique (CGFP, code des pensions civiles et militaires, lois statutaires, décrets) et codes des matières (urbanisme, commande publique, électoral, général des collectivités territoriales, sécurité intérieure, général de la propriété des personnes publiques, expropriation, voirie routière). Renvoie l'article VERBATIM dans la version applicable à la date demandée, ses autres versions et le lien Légifrance. Toujours citer le texte verbatim et la version utilisée. Avec jurisprudence=true et une référence : aussi les décisions qui citent cet article (champ « jurisprudence »). Elles ne sont trouvées que si elles citent CE numéro : pour un article du CGFP (2022), les décisions antérieures citaient l'ancienne loi statutaire ; les retrouver par rechercher_jurisprudence, en décrivant la règle en mots.

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": "rechercher_texte"
  }
}

Input Schema

Name	Required	Description
`nombre`	No
`matiere`	No	Avec `question` seulement : matière dont les textes sont interrogés (mêmes valeurs que pour rechercher_jurisprudence). Sans valeur : déterminée d'après la question.
`question`	No	À défaut de référence : question en langage naturel pour trouver les articles pertinents.
`a_la_date`	No	Date des faits (AAAA-MM-JJ) : renvoie la version applicable à cette date. Défaut : aujourd'hui.
`reference`	No	Référence d'article, ex. « article L. 530-1 du code général de la fonction publique », « article 25 de la loi du 13 juillet 1983 », « article 2-3 du décret n° 88-145 ».
`jurisprudence`	No	Avec `reference` : ajoute les décisions de Citexact qui citent ou appliquent cet article (Lebon et Conseil d'État en premier, puis les plus récentes), avec la phrase verbatim qui le mentionne.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover the read-only, idempotent, closed-world safety profile, so the description's added value is elsewhere: it discloses that the article is returned verbatim in the version applicable to the requested date, along with other versions and a Légifrance link, and it warns of a real coverage limitation in the jurisprudence mode. It does not mention result limits (the `nombre` cap of 10) or how truncation is signalled, which keeps it short of a 5.

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 scope statement is front-loaded, then the return contract, then the jurisprudence caveat — a logical order with no filler. The jurisprudence paragraph is long and dense, but each clause carries actionable routing information rather than restating the schema.

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?

An output schema exists, so return shape need not be explained; the description covers what matters instead: which corpora are searched, how date-versioning works, the citation obligation, and the known blind spot of the jurisprudence mode with the sibling that compensates for it. Nothing an agent needs to call this correctly is missing.

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?

Schema coverage is 83%, so the baseline is 3; the description still adds meaning by explaining that `a_la_date` selects the applicable historical version rather than merely filtering, and that `jurisprudence=true` is only meaningful together with a reference and only matches decisions citing that exact article number. `nombre` and the question/reference interplay remain undocumented in the description, relying on the schema.

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 a specific verb and resource (searching Légifrance LEGI texts) and enumerates the covered domains (CGFP, pensions, urbanisme, commande publique, etc.), plus what is returned (the verbatim article in the applicable version). It explicitly distinguishes itself from the sibling rechercher_jurisprudence, so an agent can route without opening either 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?

It states both when to use it (known article reference, or a natural-language question when no reference exists) and when to switch: with jurisprudence=true only decisions citing that exact number are returned, and older decisions citing a predecessor statute must be found via rechercher_jurisprudence by describing the rule in words. That is an explicit alternative with the condition that selects it.

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

All Citexact : jurisprudence administrative française tools Inspect

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

Need Help?