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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false. The description still earns credit by clarifying that reporting the 'Récupérer l'historique' button availability does NOT trigger an import — a meaningful disambiguation given the tool describes recovery behavior. It also details the shape of recovery history (truncated or not, incident or not).

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 core read-only constraint and account scope are buried mid-sentence in a single dense enumeration of return fields. It is information-rich but not front-loaded, and the long parenthetical lists make it hard to scan quickly.

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 carries the return-value burden and does so thoroughly, covering states, recovery status, defaults and filters. Minor gaps remain (whether channel and account_id can be combined), but an agent has enough to call it correctly.

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 coverage is 100%, so the schema already documents passes (default 5, max 100), the channel enum and account_id format. The description restates the passes default/limit and adds a useful cross-reference for account_id, but no new syntax or semantics. Baseline 3 is appropriate.

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 enumerates precisely what is reported for each connected account (state, last activity, last message date, cutoff date, recovery progress, recent recoveries, button availability) and notes the channel/account filters. It is clearly a status-reading tool, distinguishable from configure_channel_ai or get_stats_by_channel, though it never states the isolation from siblings explicitly.

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?

'Lecture seule : aucun import n'est déclenché d'ici' implies when the tool is appropriate (inspect state without triggering a history import), and the account_id provenance points to ficiel_list_tags_and_stages. However, there is no explicit 'use this instead of X' routing or statement of exclusions, so usage is only implied.

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