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

Annotations already declare this a read-only, idempotent, non-destructive computation, so the safety profile is covered. The description adds real behavioral context beyond them: it bills the same consumption twice with identical prices and subscription, prices must be TTC and supplied by the caller, and 'rien n'est conservé' (stateless).

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 core computation and the key negative constraint, then layers supporting detail. Every sentence carries information, though the density and slightly convoluted phrasing cost a point.

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 5-parameter tool with heavy nesting, the description supplies the essential mental model (double billing, caller-provided prices, no address resolution) and an output schema exists to cover return values. Only the omitted 'alternatives' parameter and window-structure semantics leave a 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 0%, so the description must compensate, and it only partly does: it explains that consumption can be a billed HP/HC split or annual figure and that schedules come from bill/mail. It says nothing about the optional 'alternatives' parameter, the winter/summer window structure, or the 'evidence' enum.

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 (calcule) and resource (impact d'un changement de plages d'heures creuses), and adds a scoping constraint ('deux horaires explicitement fournis, sans résoudre un horaire depuis une ville') that separates it from schedule-resolution tools. It does not name any of the sibling tools, so differentiation from simulate/run_method is left 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?

Gives clear applicability: two schedules must be supplied by the caller (from courrier or facture), consumption may be a billed HP/HC split or an annual figure, and the measured curve comes from the Boncourant study. It effectively states a when-not (no address resolves HC hours) but names no alternative tool.

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