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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and non-openWorld, so safety is covered. The description then adds genuinely useful unannotated behavior: that the output is a rendered widget rather than raw data, and that figures are computed from the same source as the app so they match. With no output schema, this disclosure of returned content carries real weight.

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-loaded with the key verb and the widget nature, then a single dense sentence enumerating contents. The long funnel listing is heavy but each item conveys what the widget returns, so it earns its place. Minor tightening possible but no filler.

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 read-only widget tool with full schema coverage and no output schema, the description supplies what the schema cannot: the rendered output form and the exact metrics shown, including prior-period comparison. What is missing is only routing against the many overlapping stats siblings.

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 both parameters (account_id, period_days) are already documented in the schema. The description restates the 30/90-day choice but adds no syntax, defaulting, or account-scoping detail beyond what the schema provides. 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 ('AFFICHE UN WIDGET' of the 30/90-day Statistics screen) and enumerates its exact contents: messages, funnel stages, response/booking rates, prior-period comparison, daily curve. It is unusually specific about what it does. The one gap is sibling differentiation: with get_stats, get_funnel, compare_periods and afficher_analyse present, it never says how it differs from them.

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?

No when-to-use, when-not-to-use, or alternative named. Given the dense cluster of overlapping statistics tools (ficiel_get_stats, ficiel_get_stats_by_channel, ficiel_get_funnel, ficiel_compare_periods), the absence of any routing guidance is a real gap. Usage can only be inferred from the data it lists.

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