Sirenic

French company health summary

get_french_company_health_summary

Read-only

Business-health and risk read-out of a French company, in French AND English, from official data only: verdict, strengths, warning signs, activity trend, confidence level, plus the reconciled grid in machine-readable codes. A model fills a closed evaluation grid (no free text, no name, no figure of its own); every number, date and sentence is assembled by Sirenic, and deterministic guards overrule the model when the filed accounts contradict it — corrections are listed in divergences_modele. Entities that file no annual accounts (non-profits, sole traders, companies under a year old, ceased companies) return verdict: "non_concluant" with most fields non_evaluable, and the prose says so explicitly — call get_french_company_profile instead if you only need identity. Cached 7 days. Paid via x402 ($0.15 in USDC or EURC).

Input Schema

TableJSON Schema

Name	Required	Description
`siren`	Yes	9-digit SIREN
`api_key`	No	Optional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402 — no wallet needed. Get one at https://api.sirenic.eu/compte. Ignored when x_payment is provided (the signed payment wins). On insufficient balance the tool returns a credits error, not an x402 quote.
`x_payment`	No	Optional signed x402 PAYMENT-SIGNATURE header value. Omit to receive the payment quote.

Output Schema

TableJSON Schema

Name	Required	Description
`hint`	No	How to settle the quote, present when payment_required is true.
`quote`	No	The 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`.
`resultat`	No	The endpoint's JSON response when payment_required is false. Paid responses carry `source`, `disclaimer` and an Ed25519 signature; KYB, batch KYB, sanctions, intelligence and the five invoicing tools (prepare_french_invoice_file, prepare_european_invoice_file, prepare_french_einvoicing_recipient, verify_iban_bank, validate_eu_vat_number) also carry a `provenance` array — one entry per block served, with the official register, licence, version, `as_of` date and `precision_as_of` (what that date means). Codes are documented at GET /v1/provenance/registres (free).
`payment_required`	Yes	True 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`.

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals substantial behavioral detail: the model fills a closed evaluation grid, deterministic guards overrule model output, corrections appear in divergences_modele, results are cached for 7 days, and payment occurs via x402. This is far more transparent than most tool definitions.

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?

The description is dense but disciplined: it front-loads the core purpose, then layers behavioral safeguards, edge cases, routing guidance, caching, and pricing. Every clause earns its place, and there is no filler or repetition of schema content.

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?

Given the output schema, parameter schema, and annotations, the description covers all necessary context: what the tool returns, how the model is constrained, what happens for non-filing entities, which sibling to use instead, and commercial details. An agent has everything needed to select and invoke this tool correctly.

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 description coverage is 100%, and each parameter already has a meaningful description in the schema, so the baseline of 3 applies. The tool description does not add parameter-specific semantics, but it also does not need to because the schema already handles it.

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 description clearly states this is a business-health and risk read-out of a French company, enumerating the exact contents: verdict, strengths, warning signs, activity trend, confidence level, and a machine-readable reconciled grid. It is distinguishable from siblings like get_french_company_profile and get_french_company_financials through its specific scope and output framing.

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?

The description explicitly routes identity-only needs to get_french_company_profile and explains the non-concluant behavior for entities without annual accounts. It does not exhaustively contrast against every financial/risk sibling, but the context provided is enough to make the main selection decision correctly.

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

All Sirenic tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation2/5

Several French company bundles overlap in purpose (get_french_company_file, get_french_company_kyb_file, get_french_company_intelligence, get_french_company_health_summary) and procurement/competitor tools overlap (get_french_company_public_procurement, get_eu_procurement_awards, get_company_procurement_competitors). Although descriptions try to differentiate, an agent could easily select the wrong tool when looking for a company overview or procurement history.

Naming Consistency4/5

Most tools follow a consistent get_/list_/search_ + country + entity pattern, e.g. get_french_company_profile, list_danish_company_filings, so navigation is predictable. Deviations like check_french_regulator_alerts, suggest_company_names, verify_iban_bank, and the prepare_* verbs are understandable but break the strict verb_noun pattern.

Tool Count1/5

77 tools is excessive for a single server regardless of how broad the domain is; the calibration treats 50+ as an extreme mismatch. While France is well covered and several countries appear, much of the surface is micro-endpoints (list_/get_ filing pairs per country) that could be consolidated.

Completeness3/5

France coverage is impressively complete (identity, financials, legal events, procurement, IP, risk, surveillance, invoicing), and the surveillance lifecycle has create/get/renew/stop. But European coverage is inconsistent: Germany has only insider transactions, Spain only acts, and several major jurisdictions lack accounts/officers/insolvency; an agent expecting 'European company due diligence' will hit dead ends.

Resources

Need Help?