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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds substantial context beyond them: the six guard checks (blacklist, protected stage, blocking tag, channel pause, follow-up cap, spacing), the fact that a refusing guard leaves the card pending with a reason, the pre-send identity comparison against the real contact, and the required write scope. This is exactly the behavioral disclosure an agent needs before an irreversible send.

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 send action in caps, and nearly every clause carries operational information (guards, preconditions, scope). It is a dense run-on paragraph rather than structured sentences, which slightly hurts scannability but wastes little.

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 destructive, non-idempotent send with no output schema, the description covers failure behavior (card stays pending, reason returned), preconditions and required scope. It does not say what a successful approval returns or whether the send is confirmed synchronously, which is the remaining gap.

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's own recipient description already spells out the case/accent-insensitive comparison, the "sans nom" convention, and the recipient_mismatch refusal. The description restates recipient's mandatory status and edited_text's 4000-character limit without adding new syntax or format meaning, so 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?

Opens with a capitalized verb+resource ("ENVOIE le message d'une carte de relance") and specifies the mechanism (the app's single send path, origine kord_card) and the target (a real contact, on behalf of the organization). This clearly separates it from ficiel_reject_card, ficiel_defer_card and ficiel_list_pending_cards, so an agent can route correctly without opening schemas.

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?

Gives clear context: the card must belong to the intended conversation, recipient must come from what ficiel_list_pending_cards returns, and text cards only. It stops short of naming the alternative actions (reject_card/defer_card) or stating when not to approve, so the routing guidance is implied rather than explicit.

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