Citexact : jurisprudence administrative française

Verifier Citation

verifier_citation

Read-onlyIdempotent

Vérifie qu'une décision citée existe dans la base (et donc qu'elle n'est pas inventée) et, si une affirmation est fournie, renvoie les passages de la décision qui s'en rapprochent le plus. À utiliser AVANT de citer une décision qui ne provient pas d'une recherche Citexact.

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": {
      "reference": "<reference>"
    },
    "name": "verifier_citation"
  }
}

Input Schema

Name	Required	Description	Default
`reference`	Yes	Référence libre : n° de requête, date, juridiction, ECLI… ex. « CE, 17 juillet 2023, n° 465121 ».
`affirmation`	No	Ce que la décision est censée juger (facultatif) : l'outil cherche les passages correspondants.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value by explaining the two-mode behavior (existence check vs. passage retrieval when an affirmation is supplied), but says nothing about what happens on a negative result or how matches are ranked.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler: the first states the validation and retrieval behavior, the second states the usage rule. The most actionable constraint is front-loaded at the end of a short, scannable block.

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 explanation, and the description covers the purpose, both parameters, and the usage trigger. Only the outcome of a failed verification and any ambiguity-handling behavior remain unspecified.

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 100%, so both parameters are already documented with examples and format hints. The description confirms the conditional role of the optional 'affirmation' parameter, but adds no syntax or interpretation guidance beyond the schema baseline.

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 ('vérifie qu'une décision citée existe dans la base') plus an explicit secondary behavior (returning the closest matching passages). This is clearly distinguishable from siblings like rechercher_jurisprudence or search, which retrieve rather than validate a citation.

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 prescribes timing and condition: use it BEFORE citing a decision that did not come from a Citexact search, which implicitly excludes citations already obtained through the search tools. No alternative tool is named by name, which keeps it just 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 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?