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) ». Accessible dès le plan gratuit, dans la limite de son quota.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | ||
| personnes | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description is not required to restate safety. It adds useful behavioral context beyond these annotations: matches are conservative, uncertain correspondences are flagged as 'à vérifier (homonyme)', and the tool has a quota limit. This is meaningful additional transparency with 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?
The description is compact and front-loaded with the core purpose, followed by the input shape, the cautionary result behavior, and access conditions. Each sentence carries useful information, though the quota/plan sentence is slightly tangential to invocation correctness.
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?
For a simple two-parameter tool, the description covers the essential input contract and the key behavioral nuance (uncertain matches are flagged). There is no output schema, but the description gives enough about result caution to prepare the agent. The main missing piece is explicit guidance on when to use this versus siblings, but that is already penalized under usage_guidelines.
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 0%, so the description must compensate, and it does: it documents the full structure of each person object, including optionality markers and expected formats such as 'YYYY-MM-DD'. The api_key parameter is not elaborated, but its purpose is self-evident from the schema. The description adds far more meaning than the minimal schema provides.
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 states a specific action ('Croise une liste de contacts') applied to a precise resource ('le registre INSEE des décès'). This clearly differentiates it from sibling tools like resoudre_siren or verifier_siret, which target SIREN/SIRET data 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?
No guidance is given on when to prefer this tool over sibling tools, nor are any exclusions or alternative tools mentioned. The only contextual note is plan/quota availability, which does not help the agent decide between croiser_deces and tools like diagnostiquer_echantillon or surveilllance_alertes.
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.
Each tool targets a clearly distinct operation and input type: people vs SIREN vs SIRET vs CRM file vs monitored portfolio. Even where data sources overlap, the entity and output differ enough that an agent can reliably choose the correct tool.
All names use lowercase snake_case with clear French domain terms, but there is a split between verb-object names like verifier_siret and nominal data endpoints like sante_entreprise. This is internally grouped and readable, though not a single uniform verb_noun pattern.
Eight tools is well-scoped for a specialized business-data and monitoring API. Each tool earns its place, and there is no redundant utility sprawl or trivial filler.
The set covers the main workflow end to end: resolve names to SIRENs, validate SIRETs, diagnose CRM quality, assess company health, inspect directors, build a monitored portfolio, and read/acknowledge alerts. No obvious dead-end operation is missing.
