nordic-data

fr_history

Read-onlyIdempotent

French company history timeline. Returns one event per change to the company's name, activity (NAF code), status (active/closed), legal form, or social-economy flag, derived from INSEE Sirene 3.11's bitemporal periodesUniteLegale array. Includes 'initial:' events that show the state at company creation (date, name, NAF code, etc.). Input: 9-digit SIREN number. Cost: 1 quota unit; free tier supported (France is not tier-gated, unlike NL and DE). Cache: 24h server-side. Errors: 400 invalid_id_format (not 9 digits), 403 non_diffusible (SIREN exists but is privacy-protected under art. R123-232-1), 404 not_found, 503 upstream_unavailable.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`siren`	Yes	9-digit French SIREN number. Examples: 652014051 (Carrefour), 775670417 (LVMH). No spaces or punctuation.

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No	Number of history events derived.
`sigle`	No	Acronym / short name, if any.
`siren`	No	9-digit SIREN echoed back.
`events`	No	Chronologically ordered events. Each event has 'initial:<field>' type for the baseline period or a plain field name for subsequent changes.
`source`	No	Upstream data source — 'api.insee.fr'.
`fetchedAt`	No	ISO-8601 timestamp when the data was fetched upstream.
`sourceNote`	No	Provenance note describing the upstream API and field set used.
`periodCount`	No	Number of bitemporal periods returned by INSEE.
`dateCreation`	No	ISO-8601 date the legal entity was created.
`categorieEntreprise`	No	INSEE company size category: PME, ETI, GE.

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedSep 15, 2026

changedOutput schema / properties / categorieEntreprise / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / count / type

Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]

changedOutput schema / properties / dateCreation / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / events / items / properties / date / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
changedOutput schema / properties / events / items / properties / type / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

changedOutput schema / properties / events / type

Previous value: -"array"New value: +[
+  "array",
+  "null"
+]

changedOutput schema / properties / fetchedAt / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / periodCount / type

Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]

changedOutput schema / properties / siren / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / source / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / sourceNote / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

AddedMay 23, 2026

TDQS

A4.5/5.0

Behavior5/5

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

The annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds concrete behavioral details: quota cost (1 unit), 24h server-side cache, and a breakdown of four error conditions with their triggers (invalid ID, privacy-protected, not found, upstream unavailable). It also reveals the internal bitemporal derivation and initial events, going far beyond annotation coverage.

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 well-structured: purpose and event types are front-loaded, then input, cost, cache, and error conditions follow in a logical order. Every sentence conveys a distinct operational detail (quota, free tier, errors) and none are wasted.

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 that output schema exists, the description covers the necessary input requirements, data scope, error semantics, caching, cost, and notifies the agent about free tier availability. This is complete enough for an agent to decide to use the tool and handle failure modes—nothing necessary is missing.

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?

The input schema has 100% description coverage, including pattern, format, and examples for the 'siren' parameter. The description's one-line 'Input: 9-digit SIREN number' adds no extra semantic information or operational nuance beyond what the schema already provides.

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 the tool's purpose: 'French company history timeline' and enumerates exactly which events are returned (name, activity, status, legal form, social-economy flag) and the data source (INSEE Sirene bitemporal periodesUniteLegale). This distinguishes it from sibling tools like lookup_company that provide current snapshots.

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 makes clear that the tool is for France and SIREN input, mentions the free tier and the 'unlike NL and DE' comparison, which implies geographic restriction. However, it does not explicitly name alternative tools or state 'when not to use this'. The usage guidance is clear but lacks an explicit exclusionary statement.

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

All nordic-data 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.