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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety bar is lower; the description nonetheless adds the crucial dual-mode semantics (no-param call is a pure read returning texts) and the preview-before-commit workflow that the annotations cannot express. It does not spell out what effacer actually destroys or that some effects (already-opened birthday gifts) are irreversible — that detail lives only in the schema.

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 and scope, then the mode semantics, then the sibling pointer — the right ordering. It is dense with nested parentheticals explaining the relance threshold rule, so a few clauses could be trimmed, but every sentence carries information the agent needs.

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?

With 25 optional parameters and no output schema, the description correctly covers the highest-risk gaps: read vs write mode, preview vs commit, partial updates, and the default/effacer path. Return values are only summarized ('rend l'état actuel, textes compris'), which is thin given the absence of an output schema, but adequate for an agent to decide and call correctly.

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% across all 25 parameters, including enum explanations and default/effacer semantics, so the schema does the heavy lifting. The description adds domain grouping (relance, anniversaire, rappels, heures calmes) but no per-parameter syntax or format detail beyond it, which is the correct baseline 3.

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 pair and resource ('lit et règle les messages que StampyWallet envoie tout seul'), then enumerates the exact sub-domains covered: relance, anniversaire, rappels with delay, heures calmes, and the Monday summary. It explicitly routes the one-off case to the sibling `envoyer_message`, so the boundary is unambiguous without opening any schema.

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 an explicit decision tree: no parameters → read current state; with changes → confirmer=false for a preview, confirmer=true to persist. It also states the partial-update rule ('seuls les champs fournis changent') and names the alternative tool for a one-off message, leaving nothing to inference.

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