Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

French company growth trajectory

get_french_company_trajectory
Read-only

Assess whether a French company is growing or shrinking using four years of filed accounts, with revenue series, peak, drop, and a trajectory classification for customer screening.

Instructions

Use when asked which customers or prospects are growing or shrinking, e.g. "Of my 300 customers, which ones have been shrinking for two years?" Growth trajectory of a French legal entity from its filed accounts ONLY: trajectoire in a closed list (croissance_forte, croissance_moderee, stable, degradation_apres_croissance, repli_modere, repli_marque, volatil_sans_tendance, serie_trop_courte, non_evaluable) on the last 4 fiscal years kept, the latest closed within 24 months, with the revenue series, peak and drop; non_evaluable carries cause_non_evaluable (aucun_compte_publie, comptes_inexploitables, comptes_trop_anciens, chiffre_affaires_non_publie), billed. signaux_hors_comptes gives establishments opened and closed over 24 months, DECP publications of contracts notified over the last 12 months vs the 12 before (an upper bound, like nombre_marches of /v1/entreprise/{siren}/marches-publics, with the source's own volume as a benchmark) and the headcount band, as dated facts, never a verdict. critere_de_liste gives the snapshot value of the tendances.trajectoire criterion of query_french_companies, which screens a whole customer file by lists of 50 SIRENs. A sole proprietor or restricted entity is refused (400, not charged); unknown SIREN 404, not charged. Paid via x402 ($0.02 in USDC or EURC). Closed lists and reading rules: GET /v1/lecture (free). When you report a result, cite its citation verbatim.

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": "get_french_company_trajectory"
  }
}

Input Schema

NameRequiredDescriptionDefault
sirenYes9-digit SIREN of a French legal entity

Output Schema

NameRequiredDescriptionDefault
hintNoHow to settle the quote, present when payment_required is true.
quoteNoThe signable x402 payment requirements when payment_required is true: {x402Version, accepts[]} where each entry carries scheme, network, amount, asset and payTo (USDC and EURC options at the same numeric amount). Sign one entry and call again with `x_payment`.
resultatNoThe endpoint's JSON response when payment_required is false. Paid responses carry `source`, `disclaimer` and an Ed25519 signature, and every paid JSON response carries a `provenance` array (all tools since 2026-09-06): one entry per block served, with the official register, licence, version, `empreinte_sha256` (full snapshots), `as_of` date and `precision_as_of` (what that date means), plus the common per-block envelope: `etat` in a closed list (servi, absence_mesuree, absence_non_conclusive, partiel, perime, indisponible, sans_objet), `motif` when unavailable, `age_jours` (only for publication or ingestion dates), `couverture` (complete / partielle / non_mesurable with its measure) and `confiance` in bands (faible / moyenne / forte, only where a measure grounds it, never averaged across blocks). Read the states before the numbers: an absence_non_conclusive, indisponible or partiel block is never « nothing to report »; only absence_mesuree asserts an absence. Register codes: GET /v1/provenance/registres ; states, closed lists and reading rules: GET /v1/lecture (both free). The PDF tools carry no JSON envelope (the PDF report prints it).
free_tierNoFree API key offer for this tool, present with a quote.
payment_requiredYesTrue when this response is an x402 payment quote instead of data: settle one of the quote's `accepts` options and call the tool again with `x_payment`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say read-only and open-world; the description adds substantially more: price ($0.02 USDC/EURC via x402), that 400 (sole proprietor/restricted entity) and 404 (unknown SIREN) are not charged, the 4-fiscal-year/24-month data window, the non_evaluable fallback causes, and that signaux_hors_comptes facts are 'dated facts, never a verdict' with contract counts being an upper bound. It also instructs citing the `citation` verbatim when reporting results.

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

Conciseness3/5

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

The usage trigger is correctly front-loaded, but the body is a dense semicolon-chained block with long inline enumerations of the trajectoire and cause_non_evaluable vocabularies. Since an output schema exists, spelling out every closed-list value is largely redundant and pushes the key operational facts (cost, error codes, citation rule) to the very end.

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?

For a single-parameter lookup with an output schema, the definition covers everything an agent needs: eligibility exclusions, error codes and billing behavior, the data freshness window, the meaning of the non-account signals including their upper-bound caveat, and the citation obligation. Nothing material is missing.

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?

Only one parameter (siren) and the schema already documents it at 100% coverage with a 9-digit pattern, so the schema carries most of the burden. The description does add modest meaning by tying the SIREN to a French legal entity and noting the sole-proprietor/restricted-entity rejection and 404 on unknown SIREN, which tells the agent what a valid input looks like.

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 — the growth trajectory of a French legal entity computed from filed accounts ONLY — and scopes it precisely (last 4 fiscal years, latest closed within 24 months). It is clearly separable from siblings such as get_french_company_financials and query_french_companies, and even explains the relationship to the latter's tendances.trajectoire criterion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Opens with an explicit when-to-use condition and a concrete user question ('Of my 300 customers, which ones have been shrinking for two years?'). It also names the alternative path for bulk work: query_french_companies screens a whole customer file in lists of 50 SIRENs, while this tool reads one entity — a genuine routing distinction rather than vague context.

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

Deploy Server

Other Tools