Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

fr_events_batch

Read-only

Check BODACC legal events for MANY companies at once (e.g. screen 700 SIRENs for collective proceedings) — batched into a few upstream requests.

Deterministic: returns a flat annonces list — one row per announcement AND per requested SIREN it names (a sale names both parties: requesting both gives two rows, same bodacc_id; a non-requested party never shows up). Each row's partie is that SIREN's role: sujet, ancien_proprietaire, ancien_exploitant, nouveau_titulaire, or indeterminee (the announcement does not say — do not guess). synthese counts on the requested SIRENs (sirens_avec_annonce, sirens_sans_annonce, par_partie, …; annonces_total = distinct announcements, lignes_total = rows).

texte is the announcement's wording for EVERY family (jugement, modification or sale descriptif… — texte_source names the field); rows the source serves without it are counted in annonces_sans_texte. It does NOT decide whether a company is in proceedings, nor what a modification changed (a director or just the auditor): read texte and judge per SIREN — counting announcements is not a signal.

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": {
      "sirens": "<sirens>"
    },
    "name": "fr_events_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
sirensYeslist of SIRENs (9 digits).
_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.
date_toNolatest publication date, inclusive (YYYY-MM-DD). A malformed date or date_from > date_to is refused; `synthese.periode` echoes the window the counts apply to. It filters on publication, not on the jugement date (`date_jugement`).
familleNoBODACC family CODE (the schema lists them). Default "collective" (procédures collectives); None = all families. The output `famille` is a LABEL ("Modifications diverses"), not an input: pass the code ("modification"). Unknown values are refused.collective
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
date_fromNoearliest PUBLICATION date, inclusive (YYYY-MM-DD). None = no lower bound (the whole history comes back).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint=true, it discloses the exact row model (one row per announcement per requested SIREN, same bodacc_id when both parties are requested, non-requested parties never appear), the meaning of `partie` including the 'indeterminee — do not guess' case, and the synthese counters. It also states important limits: it does not determine whether a company is in proceedings and does not say what a modification changed, warning that counting announcements is not a signal.

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?

Purpose is front-loaded in the first line and each following block covers a distinct topic (row cardinality, synthese, texte coverage, interpretation limits). It is dense and parenthetical-heavy, but nearly every clause carries information an agent needs to read the output correctly.

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?

With no output schema and a nine-parameter, structurally unusual response, the description fully carries the burden: it defines rows, fields (partie, bodacc_id, texte, texte_source), counters, and the rows-without-texte case. An agent could interpret results correctly from this text alone.

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, but the description adds genuine meaning about the `sirens` parameter by explaining how each requested SIREN produces its own row and role, plus the collective-proceedings framing that matches the `famille` default. It says nothing extra about date_from/date_to beyond 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 first sentence gives a specific verb and resource ('Check BODACC legal events'), an explicit scope ('for MANY companies at once') and a concrete use case ('screen 700 SIRENs for collective proceedings'), which cleanly separates it from the single-company sibling fr_events and from bodacc_notice.

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 selection condition clearly — many SIRENs, batched upstream — and even gives a scale example, so an agent knows when bulk screening is appropriate. It never names fr_events as the alternative for one-off lookups, leaving that routing step to inference.

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