Actions liées à une facture

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 safety profile is established. The description adds genuinely useful behavioral context: it explains that email sends appear as actions with recipients in `text`, that results are sorted most recent first, and that the operation is read-only ('Lecture seule'). This goes beyond what the annotations and schema provide.

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 well-structured: the purpose is front-loaded, usage guidance is clearly separated with 'Quand' and 'Plutôt que', and the behavioral note plus return description earn their place. There is no redundant filler.

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 single-parameter read-only tool with no output schema, the description is complete: it explains the returned list, its ordering, the meaning of an email-send action, and usage boundaries. An agent has everything needed to call the tool correctly.

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?

The input schema already documents the single `id` parameter with a pattern and description ('Identifiant unique de l'entité BoondManager (numérique)'), giving 100% schema coverage. The description only repeats that the action is fetched by ID and adds no new format or semantic detail, so the baseline score of 3 is appropriate.

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 ('Récupère les actions... d'un(e) facture, par son ID') and names the resource and scope clearly. It explicitly distinguishes itself from `boond_invoices_get` and `boond_invoices_search`, so an agent can differentiate it from siblings without reading their schemas.

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?

'Quand : pour ne charger que cette section, sans le reste de la fiche' gives a clear decision rule, and 'Plutôt que : ...' explicitly names the alternatives and the exact condition for choosing them. This leaves no ambiguity about when to invoke this tool versus related invoice tools.

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