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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds substantial behavioral detail beyond them: response is a single plain-text block with a specific header line, each deposit occupies two lines, ordering is newest-first, and there is no pagination. It also explains how the `limite` parameter bounds the result. No annotation contradiction exists.

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 information-dense and front-loaded with the core purpose. The bilingual French/English repetition slightly lengthens it, but every sentence contributes meaningful operational detail such as response format, ordering, limit behavior, and navigation via `archives`.

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 two-parameter read-only tool with no output schema, the description is remarkably complete: it defines the response format, ordering, non-pagination behavior, parameter constraints, defaults, and how to paginate across days using `archives`. An agent has everything needed to call the tool correctly without inspecting the schema first.

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%, and the schema already documents `jour` as UTC YYYY-MM-DD with default today and `limite` as 1–200 with default 50. The description reinforces these semantics and adds the 'no pagination' relationship and day-navigation use, but does not need to compensate for missing schema documentation.

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 verb and resource: 'Dépôts d'un jour donné' / 'Read the wall for a given day'. It also clearly delimits scope (a specific day, newest first) and references the related `archives` tool for day listings, helping an agent distinguish it from siblings like `deposer` or `fouiller`.

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?

The description gives clear operational guidance: no pagination, `limite` caps the count, and to go further back in time you pass another `jour` using `archives` to find available days. It does not explicitly list exclusion conditions versus sibling tools such as `fouiller`, but the usage context is otherwise strong.

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