Tulina

fr_groupe

Read-only

Ownership chain of a French company — qualify its INDEPENDENCE, or inventory a group.

⚠️ confiance="indeterminee" (no parent reached) does NOT mean "independent": the beneficial-owners register has been closed to the public since 31/07/2024. motifs_indetermination says why — including sans_siren: legal-entity officer without a SIREN (often foreign), returned in exclus.sans_siren (name, capacity). No parent is an ANSWER. ⚠️ Going down, the upstream caps at 25 results/page and 10,000 in total: candidats_tronques=true signals a sample, not an inventory.

op:

"ascendant" (default): goes up the legal-entity officers, BREADTH-first (a company often has several parents at the same level). Returns {tetes, liens, confiance, cycle, tronque}.
"descendant": entities controlled by this SIREN — one call instead of N.

Why: categorie_entreprise (PME/ETI/GE) is computed by INSEE at the GROUP level, never at the entity level — a tiny subsidiary comes out as "GE".

confiance per link: forte = the capacity implies ownership (limited partner / unlimited liability) · moyenne = corporate office (chair, director, manager): governance proven, control suggested · faible = neither (GIE member, liquidator) · inconnue = unlisted capacity. Only forte and moyenne are traversed. Statutory audit is excluded (commissaire OR contrôleur, counted in exclus).

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": {
      "siren": "<siren>"
    },
    "name": "fr_groupe"
  }
}

Input Schema

Name	Required	Description	Default
`op`	No	ascendant (default) \| descendant.	ascendant
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`siren`	Yes	Company SIREN (9 digits).
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`_run_id`	No	OBLIGATOIRE 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.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`max_depth`	No	op="ascendant" — levels climbed (default 4, max 6).
`max_pages`	No	op="descendant" — pages of 25 candidates examined (default 4, max 20).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0

Behavior5/5

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

Far beyond the readOnlyHint annotation: the description discloses that the beneficial-owners register has been closed to the public since 31/07/2024, so `confiance="indeterminee"` is not proof of independence, and it explains `motifs_indetermination`, `sans_siren` / `exclus.sans_siren`. It also warns, unusually usefully, that upstream caps at 25 results/page and 10,000 total so `candidats_tronques=true` means a sample rather than an inventory, and it states that statutory audit is excluded from traversal.

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?

Long but front-loaded and sectioned: purpose first, then the two warnings, then the `op` bullets, then the `confiance` key. Dense jargon (PME/ETI/GE, GIE, commissaire aux comptes) is used precisely rather than decoratively. A small amount of the framing (the INSEE group-level rationale) borders on tutorial, but every line carries usable decision content.

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 9 parameters, no output schema, and a genuinely subtle result vocabulary, the description carries the return shape it needs to: named result keys, the confidence scale, cycle and truncation flags, and the ownership caveat. What remains thin is operational: no guidance on cost/latency trade-offs of raising `max_depth` or `max_pages`, and the `_run_id` / `_org` / `_project` plumbing is only handled by the schema.

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 earns above that by giving real semantics to `op` (breadth-first ascent with returned keys `{tetes, liens, confiance, cycle, tronque}`; descendant as a batch substitute for N calls) and by spelling out the `confiance` vocabulary (forte/moyenne/faible/inconnue) and which levels are traversed. It adds little for `max_depth` / `max_pages` beyond what the schema's own descriptions already say.

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?

Opens with a specific verb+resource+intent: "Ownership chain of a French company — qualify its INDEPENDENCE, or inventory a group." That single line tells an agent both what is returned (a chain) and the two jobs it serves, and the `op` bullets make the ascendant/descendant split unambiguous 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?

Strong internal routing: `ascendant` is stated as the default with breadth-first behaviour (multiple parents at one level), and `descendant` is recommended as "one call instead of N", which is an explicit when-to-use-this-branch rule. It does not name or contrast any sibling tool (e.g. fr_bilans, fr_directors, waterfall_company), so an agent gets op-level guidance but no cross-tool disambiguation.

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

All Tulina 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?