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

Annotations only supply readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the interaction model (a drag-and-drop card, not a model-supplied argument), the 15 MB size cap, that the file goes directly to the third-party MaFactureOK service and is deleted after analysis, and exactly what the card returns (verdict, per-anomaly French explanations with expected correction, company registry status).

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?

It is one dense but well-ordered paragraph: mechanism first, then output, then the usage trigger, then the no-argument note. Every clause carries information, though the single-block format and long sentence make it slightly harder to scan than a split structure would.

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 no output schema, the description fully carries the return contract (verdict values, anomaly explanations, registry status) and the input contract (formats, size limit, privacy handling). Nothing needed to invoke or interpret the result is missing.

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 schema is empty (0 parameters), so the baseline is 4, but the description adds real meaning: "Aucun argument : le fichier n'est jamais transmis par le modèle" explains both the absence of parameters and the mechanism by which input reaches the tool, removing any temptation for the agent to construct a file argument.

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 and resource (opens an upload card to verify an e-invoice) and names the accepted formats (PDF Factur-X, XML UBL/CII), the verdict outcomes, and the registry check. This clearly separates it from the sibling checks verifier_tva, verifier_tiers and expliquer_code_rejet.

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?

"À appeler dès que l'utilisateur veut vérifier, valider ou comprendre le rejet d'une facture qu'il possède en fichier" gives an explicit trigger plus an implicit boundary (the invoice must exist as a file). It never names the sibling tools as alternatives, so the routing is inferred rather than spelled out.

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