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

Goes well beyond the annotations: it discloses the billing consequence ('compté dans le forfait mensuel de conversations'), that no message is sent, that nothing is deleted ('un brouillon périmé est marqué remplacé, jamais effacé'), that sending requires a human click, and that the `text` override is display-only and not persisted. The readOnlyHint=false is consistent with the tool creating/reusing a draft, and idempotentHint=true is corroborated by the reuse rule.

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 action in caps, then the state rules, then the two side-effect disclaimers — good ordering. The paragraph is dense but nearly every clause carries decision-relevant information; only the parenthetical quota reminder is slightly tangential.

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 2-parameter tool with annotations but no output schema, the description covers everything an agent needs: what appears in the widget, idempotent reuse behavior, cost, non-persistence of the override, and the fact that sending is a separate user action. No hidden side effect is left unstated.

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 a 3 would suffice, but the description adds real semantics for `text` beyond the schema's 'remplace celle de Kord dans la carte': it is only displayed, not recorded, and Kord's underlying draft is preserved. The conversation_id linkage to sibling tools lives in the schema, not the description.

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 opening states a specific verb and resource in caps ('AFFICHE UN WIDGET : la relance préparée par Kord pour UNE conversation'), with the widget's contents enumerated. It implicitly separates itself from send/prepare siblings ('Aucun message n'est envoyé', 'comme le lot de relances de Ficiel') but never names ficiel_envoyer_relance or ficiel_prepare_followup as the alternatives, so differentiation is inferred rather than explicit.

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?

Usage is implied by the widget metaphor and by the reuse rule ('Si une relance attend déjà... elle est reprise telle quelle'), which tells the agent the call is safe to repeat. However, there is no explicit statement of when to call this versus ficiel_prepare_followup or ficiel_envoyer_relance, and no when-not guidance.

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