messagerie_non_lus

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the scoping detail that the count is limited to the inbox (boîte de réception), which is useful given the sibling messagerie_dossiers exists. It does not disclose the return shape or whether it counts all folders.

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?

A single short sentence with zero filler, and the scope (inbox) is front-loaded into the resource phrase. Nothing to trim.

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 trivial zero-parameter count tool whose annotations cover the safety profile, this is nearly sufficient. However, with no output schema, the description does not confirm the return type (a number) or whether folders other than the inbox are excluded, leaving minor ambiguity.

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, so there is nothing for the description to disambiguate. Baseline 4 applies; no syntax or format guidance is needed.

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 names a specific resource and quantity: the count of unread messages in the inbox. It is clearly distinguishable from messagerie_lister (which lists messages) and messagerie_lire (which reads one), since this is a scalar count. It does not explicitly name a sibling, so it falls short of a 5.

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?

There is no when-to-use guidance and no mention of alternatives. An agent must infer that this is for a lightweight badge/count check rather than fetching messages. Usage is only implied by the noun phrase.

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