Citexact : jurisprudence administrative française

Rechercher Conclusions

rechercher_conclusions

Read-onlyIdempotent

Recherche dans les conclusions des rapporteurs publics du Conseil d'État publiées sur ArianeWeb (environ 3 600 : fonction publique et, avec le paramètre matiere, matières de l'élargissement). Renvoie, pour chaque conclusion : le rapporteur public, la décision rendue (à vérifier avec fetch), de COURTES citations verbatim et le lien vers le PDF officiel. Utile pour comprendre un raisonnement, une évolution de jurisprudence ou les arguments écartés. Le texte intégral n'est pas reproduit (droits d'auteur).

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": {
      "question": "<question>"
    },
    "name": "rechercher_conclusions"
  }
}

Input Schema

Name	Required	Description
`nombre`	No	Nombre de conclusions (défaut 4).
`matiere`	No	Matière où chercher (mêmes valeurs que pour rechercher_jurisprudence). Sans valeur : déterminée d'après la question.
`question`	Yes	Question de droit ou raisonnement recherché, en français.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses corpus size and default coverage (fonction publique only, broadened via `matiere`), the shape of the returned excerpts ('COURTES citations verbatim', PDF link), and a real constraint: full text is not reproduced for copyright reasons. The instruction to verify the rendered decision with `fetch` warns the agent about potential attribution error.

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?

What it does, what it returns, and its limits are front-loaded, with every clause carrying information. The single dense block with embedded line breaks is slightly harder to scan than a short structured list would be, but there is no filler.

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?

With an output schema present, return values need no further explanation, and the description still covers corpus boundaries, excerpt nature, copyright limits, and verification duty. Only an explicit statement of when a different search sibling is preferable is missing for full completeness on a search tool.

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 100%, so the baseline is 3. The description adds genuine meaning by explaining that without `matiere` the corpus defaults to fonction publique and that supplying it opens the 'matières de l'élargissement' — a behavioral consequence the enum alone does not convey.

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 ('Recherche dans les conclusions des rapporteurs publics du Conseil d'État') and pins the source corpus ('ArianeWeb, environ 3 600'). It distinguishes itself from the sibling search tools by scope, and explicitly hands off decision verification to 'fetch'.

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?

It states the substantive use cases clearly: 'comprendre un raisonnement, une évolution de jurisprudence ou les arguments écartés'. It also gives the follow-up rule ('la décision rendue (à vérifier avec fetch)'). It does not explicitly contrast itself with 'rechercher_jurisprudence' or 'rechercher_texte', so the choice between them is still partly inferred.

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?