get_enterpriseFetch a single legal unit with all its establishments by SIREN (9 digits).
| Name | Required | Description | Default |
|---|---|---|---|
| siren | Yes | 9-digit SIREN identifier |
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Current page (always 1) | |
| results | No | Array with single legal unit (or empty if not found) | |
| per_page | No | Results per page (always 1) | |
| total_results | No | Total number of matching results (0 or 1) |
Changes observed during successful MCP inspections.
Output schema / properties / results / items / properties / sigle / typePrevious value: -"string"New value: +[
+ "string",
+ "null"
+]Input schema / examplesPrevious value: -[
- {
- "siren": "123456789"
- }
-]New value: +[
+ {
+ "siren": "552032534"
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "siren": "123456789"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "page": {
+ "description": "Current page (always 1)",
+ "type": "number"
+ },
+ "per_page": {
+ "description": "Results per page (always 1)",
+ "type": "number"
+ },
+ "results": {
+ "description": "Array with single legal unit (or empty if not found)",
+ "items": {
+ "properties": {
+ "address": {
+ "description": "Registered address",
+ "type": "string"
+ },
+ "ape": {
+ "description": "APE/NAF activity code",
+ "type": "string"
+ },
+ "city": {
+ "description": "City name",
+ "type": "string"
+ },
+ "denomination": {
+ "description": "Legal unit name",
+ "type": "string"
+ },
+ "departement": {
+ "description": "French département code",
+ "type": "string"
+ },
+ "dirigeants": {
+ "description": "Directors and managers",
+ "items": {
+ "properties": {
+ "fonction": {
+ "description": "Role/title",
+ "type": "string"
+ },
+ "nom": {
+ "description": "Director name",
+ "type": "string"
+ },
+ "prenom": {
+ "description": "Director first name",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "etablissements": {
+ "description": "All registered establishments",
+ "items": {
+ "properties": {
+ "address": {
+ "description": "Establishment address",
+ "type": "string"
+ },
+ "city": {
+ "description": "City name",
+ "type": "string"
+ },
+ "enseigne": {
+ "description": "Trading name",
+ "type": "string"
+ },
+ "etat_administratif": {
+ "description": "Status (A=active, R=closed)",
+ "type": "string"
+ },
+ "postal_code": {
+ "description": "5-digit postal code",
+ "type": "string"
+ },
+ "siret": {
+ "description": "14-digit SIRET identifier",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "etat_administratif": {
+ "description": "Administrative status (A=active, R=radiated)",
+ "type": "string"
+ },
+ "labels": {
+ "description": "RGE eco-labels or certifications",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "postal_code": {
+ "description": "5-digit postal code",
+ "type": "string"
+ },
+ "sigle": {
+ "description": "Abbreviated name or acronym",
+ "type": "string"
+ },
+ "siren": {
+ "description": "9-digit SIREN identifier",
+ "type": "string"
+ },
+ "tranche_effectif_salarie": {
+ "description": "Employee count band",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "total_results": {
+ "description": "Total number of matching results (0 or 1)",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds the scoping detail 'with all its establishments,' which is useful but not a deeper behavioral disclosure (e.g., error cases, data freshness). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that names the action, resource, and criterion with zero filler. Each element earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one well-documented parameter, a rich output schema, and complete safety annotations, this description is sufficient for an agent to invoke the tool correctly. Nothing essential is missing, aside from the optional usage guidance already scored separately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the siren parameter is fully documented. The description's '(9 digits)' merely restates the schema and does not add new semantic meaning beyond it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Fetch'), the resource ('single legal unit with all its establishments'), and the key identifier ('by SIREN (9 digits)'). This distinguishes it from generic search tools, but it does not explicitly contrast it with similar sibling entity lookups like entity_profile or resolve_entity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the usage condition: call this when you have a 9-digit SIREN and need the legal unit plus all its establishments. However, it provides no explicit when-to-use vs. alternatives guidance, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.