Skip to main content
Glama

search_directors

Read-onlyIdempotent

Recherche de personnes (dirigeants) à travers toutes les sociétés françaises, par nom de famille.

À la différence de search_companies (qui retourne des ENTREPRISES et accepte dirigeant_nom/dirigeant_prenom comme filtres), search_directors retourne directement des PERSONNES avec leur société de rattachement. Cas d'usage : "toutes les sociétés où siège un dirigeant nommé DUPONT", cartographie d'un réseau de mandats.

Paramètres : nom (REQUIS, nom de famille), prenom (optionnel, désambiguïse), role (optionnel, ex "Président", "Gérant", "Administrateur"). Par défaut seuls les mandats actifs ; include_inactive=true pour inclure les anciens mandats.

Réponse : data[] = personnes { nom, prenom, civilite, role, role_description, date_naissance, annee_naissance, lieu_naissance, type_personne, linkedin_url, entreprise { siren, denomination, ville, departement, code_ape } }. linkedin_url n'est présent que si un profil a été apparié avec certitude ; son absence est le cas courant, pas une anomalie. pagination { total (nb sociétés matchées), limit, returned }.

Homonymes : un même nom+prénom recouvre souvent plusieurs personnes distinctes. date_naissance est le champ qui les distingue : deux dates différentes = deux personnes ; date absente = identité non confirmée ; même date = même personne. La date est diffusée au MOIS (jour normalisé à 01), conformément au régime de diffusion du registre : deux personnes nées le même mois restent indistinguables.

Pour lister TOUTES les sociétés d'une personne donnée une fois sa date de naissance connue, enchaîner avec search_director_companies (nom + prénom + date_naissance). Pour la fiche complète d'un dirigeant d'une société donnée, utiliser get_directors avec le SIREN.

COÛT en crédits : 0,1 par personne retournée ; au quota : 1 unité par recherche.

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": {
      "nom": "<nom>"
    },
    "name": "search_directors"
  }
}

Input Schema

NameRequiredDescriptionDefault
nomYesNom de famille du dirigeant recherché (requis).
roleNoRole/qualite (optionnel), ex: 'Président', 'Gérant', 'Administrateur'.
limitNoNombre de sociétés à scanner (défaut 20, max 20).
prenomNoPrénom (optionnel) pour désambiguïser les homonymes.
include_inactiveNoInclure les mandats inactifs (par défaut : false).

Output Schema

NameRequiredDescriptionDefault
dataNo
_accessNo
_user_planNo
paginationNo
_quota_remaining_monthNo
_quota_remaining_todayNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  2. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre de sociétés à scanner (défaut 20, max 50)."New value: +"Nombre de sociétés à scanner (défaut 20, max 20)."
    • addedOutput schema / properties / _access / properties / companies_remaining_30d
      Added value: +{
      +  "type": "number"
      +}
    • removedOutput schema / properties / _access / properties / companies_remaining_7d
      Removed value: -{
      -  "type": "number"
      -}
  3. Changed1 schema field changed
    • addedOutput schema / properties / _access
      Added value: +{
      +  "additionalProperties": {},
      +  "properties": {
      +    "companies_remaining_24h": {
      +      "type": "number"
      +    },
      +    "companies_remaining_7d": {
      +      "type": "number"
      +    },
      +    "message": {
      +      "type": "string"
      +    },
      +    "mode": {
      +      "description": "normal | slowed",
      +      "type": "string"
      +    },
      +    "search_rows_remaining_24h": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "mode"
      +  ],
      +  "type": "object"
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre d'entreprises à scanner (défaut 20, max 50)."New value: +"Nombre de sociétés à scanner (défaut 20, max 50)."
  5. Changed5 schema fields changed
    • changedInput schema / properties / include_inactive / description
      Previous value: -"Inclure les mandats inactifs (defaut: false)."New value: +"Inclure les mandats inactifs (par défaut : false)."
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre d'entreprises a scanner (defaut 20, max 50)."New value: +"Nombre d'entreprises à scanner (défaut 20, max 50)."
    • changedInput schema / properties / nom / description
      Previous value: -"Nom de famille du dirigeant recherche (requis)."New value: +"Nom de famille du dirigeant recherché (requis)."
    • changedInput schema / properties / prenom / description
      Previous value: -"Prenom (optionnel) pour desambiguiser les homonymes."New value: +"Prénom (optionnel) pour désambiguïser les homonymes."
    • changedInput schema / properties / role / description
      Previous value: -"Role/qualite (optionnel), ex: 'President', 'Gerant', 'Administrateur'."New value: +"Role/qualite (optionnel), ex: 'Président', 'Gérant', 'Administrateur'."
  6. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / llm_model
      Removed value: -{
      -  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "nom",
      -  "llm_model"
      -]New value: +[
      +  "nom"
      +]
  7. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "nom"
      -]New value: +[
      +  "nom",
      +  "llm_model"
      +]
  8. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  9. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  10. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  11. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  12. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  13. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  14. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  15. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  16. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  17. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  18. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  19. Changed1 schema field changed
    • removedOutput schema / properties / _credits_remaining
      Removed value: -{
      -  "type": "number"
      -}
  20. Changed1 schema field changed
    • addedOutput schema / properties / _credits_remaining
      Added value: +{
      +  "type": "number"
      +}
  21. Changed1 schema field changed
    • changedOutput schema / properties / pagination / additionalProperties
      Previous value: -falseNew value: +{}
  22. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
      -  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "nom",
      -  "context"
      -]New value: +[
      +  "nom"
      +]
  23. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "nom"
      -]New value: +[
      +  "nom",
      +  "context"
      +]
  24. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the supplied readOnly/idempotent annotations, the description discloses the credit cost (0.1 per person, 1 unit per search at quota), the default active-mandate-only behavior, the month-granularity birth-date diffusion rule, and that an absent linkedin_url is normal rather than an error. It also explains the homonym disambiguation logic, which is the main failure mode for this tool.

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?

It is long but well-structured and front-loaded: purpose, contrast, use cases, parameters, response, homonyms, chaining, cost. Each section earns its place, though the response-shape paragraph duplicates detail an output schema likely already carries.

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 search tool with an output schema, it still explains return semantics (pagination total means matched companies, not people), the homonym/date rule, and the chaining workflow. An agent has everything needed to call it correctly and interpret results.

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 already 100%, so the baseline is 3, but the description adds real meaning: nom is the surname, prenom disambiguates homonyms, role examples ('Président', 'Gérant', 'Administrateur'), and include_inactive expands to old mandates. The `limit` parameter is only implicitly covered via the pagination note, which is the only gap.

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 gives a specific verb and resource ('Recherche de personnes (dirigeants) à travers toutes les sociétés françaises, par nom de famille') and immediately differentiates itself from search_companies by contrasting ENTREPRISES vs PERSONNES returns. An agent can distinguish it from get_directors and search_director_companies without opening any schema.

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?

It supplies explicit use cases ('toutes les sociétés où siège un dirigeant nommé DUPONT', réseau de mandats) and names the alternatives with the conditions that select them: search_director_companies when the birth date is known, get_directors by SIREN for a company-specific fiche. Nothing is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources