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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral details beyond those: it explicitly states the double-billing methodology, that prices are caller-supplied and tax-inclusive, and that 'nothing is retained' – a useful data-retention disclosure not present in annotations.

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 dense sentences, each earning its place. The primary purpose is front-loaded in the first sentence, followed by methodology and input-source constraints. There is no filler or repetition.

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 tool with a complex five-parameter nested schema and an output schema, the description covers the core calculation, input sources, consumption types, pricing, and retention. It omits explicit discussion of the 'alternatives' parameter, but the overall guidance is sufficient for correct invocation, especially with the structured schema present.

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?

With 0% schema description coverage, the description carries the burden. It interprets the 'consumption' parameter by naming the two accepted forms (billed split vs annual consumption) and points to the Boncourant study for the measured curve. However, it does not explain other parameters like 'alternatives' or 'current_option', leaving those to schema inference. It adds some meaning but not comprehensive coverage.

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: 'Calcule ce qu'un changement de plages d'heures creuses coûte à l'année' (calculates what a change in off-peak hour ranges costs per year). It clearly distinguishes this from siblings by focusing on the cost impact of schedule changes, and it even explains the method (billing the same consumption twice).

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?

The description gives practical context: schedules come from mail or invoice, no address can resolve off-peak hours, and the measured curve is read from the Boncourant study. It clarifies input sources and acceptable consumption formats (billed HP/HC split or annual consumption), though it does not explicitly name alternatives or say when not to use this tool.

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