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

Goes well beyond the annotations by disclosing that nothing is sent, that the rejection feeds Kord's learning, and that for daily-batch cards the contact is additionally removed from follow-ups via an 'Ignorer' tag that is reversible from the contact sheet. That is exactly the side-effect and reversibility information an agent needs for a non-readOnly write. No contradiction with destructiveHint=false, since the tag removal is explicitly described as removable.

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-loads the core effect ('Écarte... sans rien envoyer') and then qualifies it with the conditional exclusion rule, the text-only restriction and the scope requirement. Dense but every clause carries a distinct constraint; the parenthetical about the app/tag origin is slightly incidental.

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 write tool with no output schema, the description covers the constraints, the conditional side effect and the required scope. It stops short of saying what the call returns (e.g. whether the tag or the learning update is echoed back), which would be the only 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 coverage is already 100%, so the baseline is 3, but the description adds real meaning to confirm_exclusion: it is only demanded for daily-batch cards and true authorizes removal of the contact from follow-ups. card_id itself is left to the schema, which is fine given its full 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?

States a specific verb and resource ('Écarte une carte de relance') plus a key differentiator: nothing is sent, unlike sending tools. It does not explicitly name the neighbouring choices (approve_card, defer_card, ne_plus_proposer), so the boundary with those siblings must be inferred.

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 through constraints (text cards only, write scope, confirm_exclusion required for daily-batch cards) but there is no explicit statement of when to reject rather than defer or approve a card. The conditional rule for the daily batch is well specified, but the choose-this-tool guidance is left implicit.

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