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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by disclosing sort order, the four delivery-status buckets, the automatic-message summary over the period, and the 'can a message still go out today' signal. It does not mention pagination behavior or result size limits, which the schema only partially covers.

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?

Front-loads the core action and result content, then closes with usage guidance. It is somewhat long, but each clause carries distinct information (ordering, status buckets, automatic summary, usage triggers) rather than restating the name.

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 must convey return content, and it does: per-message delivery status plus an aggregate summary of automatic messages and a same-day sendability indicator. Only pagination/truncation behavior and the shape of the summary are left implicit.

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 description coverage is 100%, so all four parameters (depuis, jusqu_au, limite, decalage) are already documented, including the default 30-day window for the automatic summary. The description itself adds no parameter-level detail, so the baseline 3 applies.

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 specific verb and resource ('Liste les messages déjà envoyés aux clients') plus ordering (du plus récent au plus ancien) and the exact content of the result (bilan de remise: reçus, sans écran, échecs, en cours). This clearly separates it from envoyer_message and lister_messages_recurrents, which deal with composing or recurring templates rather than sent history.

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?

Gives three concrete use cases: knowing what was sent, verifying delivery, and checking before writing a new message. That last clause implicitly routes the agent to envoyer_message afterwards, but no sibling is named explicitly and no exclusion ('ne pas utiliser pour…') is stated.

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