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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the trailing "Lecture seule" is redundant rather than additive. The only extra behavioral fact is that the returned example uses fictitious data, which is useful but thin; with annotations carrying the safety profile, the lower bar is met at a 3.

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?

One sentence, no preamble, front-loaded with the primary return value (the schema) followed by the secondary artifacts and the read-only reassurance. Nothing could be removed without losing information.

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?

With an output schema present, the description needn't detail field-level return values, and annotations cover safety, so the essentials are in place. The one gap is that the chaining mechanics are asserted rather than explained (whether the schema is passed to convert_to_facturx or merely consulted), leaving a small amount of inference.

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 tool takes zero parameters, which is the baseline-4 case, and the description correctly implies a parameterless call. The « invoice » token belongs to convert_to_facturx's parameter, not this tool's, so it adds chaining value rather than parameter semantics here.

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?

States a concrete verb ("Renvoie") and enumerates exactly what comes back: the invoice JSON schema, a valid example with fictitious data, and Excel/CSV template links. It also names the sibling it pairs with (convert_to_facturx, source « invoice »), so an agent can tell it apart from the other get_*/validate_* tools without opening a schema.

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?

Explicitly positions the tool as the input-side companion to convert_to_facturx and pins the required source value (« invoice »), which is genuine when-to-use guidance. It stops short of when-not-to-use (e.g. that it returns nothing conversion-specific and validate_facturx must run afterwards), so it is clear context rather than full routing.

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