Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

loi_article

An article of a French consolidated code (LEGI) — its text as in force at a given date, its version timeline, or finding it by concept.

THE tool for citing law: exact text + verifiable Légifrance URL.

op:

  • "get" (default): consolidated text of a French code article (code + num), as in force at a given date.

  • "versions": full version timeline of a code article (code + num) — every rewriting with dates and statuses. Use to see WHEN an article changed before picking a date for op="get".

  • "search": full-text search across French consolidated codes (LEGI). Find the article when you know the concept but not the number ("période d'essai CDD", "clause de non-concurrence").

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": "loi_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNoget (default) | versions | search.get
numNoop="get"/"versions" — article number, ex "L1242-2", "1128", "R4228-20".
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
codeNoop="get"/"versions" (required) — short alias: CT (travail), CC (civil), CP (pénal), CSS (sécurité sociale), CCOM, CGI, CPI… (loi_codes lists all 22) — or a raw LEGITEXT id. op="search" (optional) — restrict to one code (alias CT/CC/… or LEGITEXT).
dateNoop="get" — YYYY-MM-DD, version in force AT THAT DATE (default: today). Use the date of the document citing the article: a 1992 ruling cites the 1992 wording, not today's.
limitNoop="search" — max results (default 20, max 50).
queryNoop="search" — full-text query (websearch syntax, french stemming).
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
_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')`.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
en_vigueurNoop="search" — only versions in force today (default True).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the meaningful behaviors: each op's return content (consolidated text at a date, every rewriting with dates and statuses, search hits), the URL verifiability claim, and the default-to-today date semantics. It stops short of covering result-size behavior, failure modes for unknown article numbers, or that 'get' at a past date may return a superseded version's wording rather than an error.

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?

Front-loaded with the identity and the differentiator (citable text plus verifiable Légifrance URL), then a tight bulleted op list where every line describes one mode and its discriminating use case. No filler sentences and no repetition of the schema's plumbing parameters.

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?

For a 12-parameter, three-mode tool with no annotations and no output schema, the description covers the opaque parts: what each op does, what it returns in prose (text, timeline, results), and how to choose a date. The five underscore-prefixed context parameters are left entirely to their schema descriptions, which is acceptable, but the lack of an output schema means the description could say more about the shape of a search hit or a versions entry.

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 parameter documentation is already complete; the baseline is 3. The description does add real meaning beyond the schema for `date` (use the date of the document citing the article, since a 1992 ruling cites the 1992 wording) and for `code` aliases (CT, CC, CSS…), but this is reinforcement of schema text rather than net-new semantics.

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 opening sentence names the specific resource (a LEGI consolidated code article) and the three things it can deliver: text in force at a date, version timeline, or concept lookup. The op-by-op breakdown then maps each mode to a concrete verb+resource, so an agent can distinguish 'get', 'versions' and 'search' 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 Guidelines4/5

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

Usage is explicit within the tool: use op="versions" to see WHEN an article changed before picking a date for op="get", and op="search" when you know the concept but not the number, with concrete French query examples. It also states the date-selection rule (cite the wording in force when the citing document was issued). What is missing is guidance relative to external siblings such as ccn_article or loi_codes — the example query "période d'essai CDD" could plausibly live in a convention collective, yet no routing hint is given.

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