Croise une liste de contacts avec le registre INSEE des décès. Chaque personne : {"nom": str, "prenom": str, "annee_naissance": int?, "date_naissance": "YYYY-MM-DD"?, "code_postal": str?, "ref": str?}. Résultat prudent : les correspondances non certaines sont marquées « à vérifier (homonyme) ». Réservé aux plans payants (starter+).
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | ||
| personnes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds valuable behavioral context: the cautious result marking ('à vérifier (homonyme)') and the paywall requirement, which go beyond the structured annotations. No contradictions found.
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?
The description is compact and front-loaded, stating the main action immediately. It uses an efficient JSON-like notation for the person structure and includes only essential information (result marking, paywall). Every sentence contributes meaning without redundancy.
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?
The tool is moderately complex and has no output schema, so the description should explain return values. It only hints at the output by mentioning uncertain matches marked 'à vérifier (homonyme)', but does not describe the overall result format, success/error conditions, or rate limits. It adequately covers input structure but leaves gaps on output and edge behavior.
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?
With schema description coverage at 0%, the description compensates significantly by detailing the inner structure of 'personnes' (nom, prenom, annee_naissance, date_naissance, code_postal, ref) with types and optionality. However, the 'api_key' parameter is not described beyond its requirement, and the outer array semantics are only implied by the person object definition.
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 uses a specific verb ('Croise') referring to a specific resource ('registre INSEE des décès') and object ('liste de contacts'), making its purpose unambiguous. It clearly distinguishes itself from sibling tools like resoudre_siren and verifier_siret which target business identifiers rather than death records.
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 states a clear usage restriction ('Réservé aux plans payants (starter+)') and provides context (cross-referencing contacts against the death register). However, it does not explicitly mention when not to use it or name alternative tools, though the context is sufficient for basic selection.
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.
Most tools have clearly distinct purposes (e.g., name-to-SIREN resolution vs SIRET verification), but croiser_deces and dirigeants_entreprise both involve death-registry matching, and the pair resoudre_siren/verifier_siret could initially confuse. However, the descriptions disambiguate well.
The naming mixes infinitive verbs (resoudre, verifier, croiser, diagnostiquer) with noun phrases (sante_entreprise, dirigeants_entreprise, surveillance_alertes), so there's no uniform verb_noun or noun pattern. Still, the names are reasonably readable and not chaotic.
With 8 tools, the server covers the core workflows of data validation, enrichment, scoring, and monitoring without bloat. Each tool addresses a distinct business need, and the count is well within the ideal range.
The surface covers identification, verification, scoring, and portfolio monitoring, but lacks a simple company detail retrieval endpoint (e.g., by SIREN) and a tool for updating/deleting non-portfolio data. These are minor gaps that can be worked around.
