Préavis

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is fully covered and the description carries a lighter burden. It usefully states that the result is a duration plus an end date, but adds nothing about how legal/conventionnel precedence is arbitrated at runtime or what happens when required data is missing.

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?

A single front-loaded sentence naming the computation, its outputs, and the starting input, with no filler. The parenthetical rupture-type list earns its place by scoping the tool.

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 no output schema, the description does the necessary work by naming both return values (durée and date de fin). For a nine-parameter, two-required pure calculation tool the main remaining gap is per-type parameter applicability, which the schema partially covers via its enum documentation.

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 67%, so roughly a third of the nine parameters (cadre, ancienneteMois, ancienneteAnnees) are documented only by name. The description does not clarify which optional parameters matter for which rupture type (e.g. presenceJours only for essai, dureeConventionnelleMois only when more favourable), so it adds little beyond the schema's own enum 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?

Specific verb (calcule) plus two concrete outputs (durée du préavis, date de fin) and an explicit input basis (date de notification). It also enumerates the covered rupture types (démission, licenciement, rupture de période d'essai), which cleanly separates it from siblings like indemnite_licenciement or rupture_conventionnelle.

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 only implied: the sentence establishes that the calculation starts from the notification date, so an agent can infer it is a calculation helper. There is no explicit when-to-use/when-not statement and no sibling is named as an alternative, even though indemnite_licenciement and rupture_conventionnelle overlap in domain.

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