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

Annotations already disclose a non-read-only, non-idempotent, open-world write, so the bar is lower; the description still adds real value by explaining the two-phase lifecycle (secret action_id, 10-minute validity, provisional record erased if unconfirmed). It omits any note on authorization requirements or what happens on retry within the TTL window, but the erasure/TTL disclosure is well beyond annotation coverage.

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?

Three tight sentences, front-loaded with purpose, then the hard constraint, then the return/lifecycle behavior. Every clause carries information and nothing is repeated from the schema.

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 two-step, consent-gated write with no output schema, the description covers purpose, precondition, returned token, TTL and cleanup semantics. The only gap is that it never names the confirmation sibling the agent must call next, which the agent has to infer from the sibling list.

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 baseline would be 3, but the description resolves a genuine schema ambiguity: the schema lists only email as required and gives consent a default of false, whereas the description states consent=true is in fact obligatory for the write to be valid. That is meaning the agent could not derive from the structured fields alone.

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 opens with a specific verb and resource ('Je prepare une demande de rappel') and flags it as a consented write, so the agent knows exactly what is being created. It does not explicitly name the sibling tools (confirmer_action, annuler_action) that make up the surrounding workflow, leaving that differentiation implicit.

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?

Preconditions are stated clearly: a consent flag is mandatory and the email must belong to the person herself, which effectively rules out third-party submissions. It stops short of naming when to choose this over statut_actions or how the follow-up confirmation step maps to confirmer_action.

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