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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds that it returns a total bill, but says nothing about what the result breakdown contains or how consumption above a band is handled — small added value over the structured fields.

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?

Four short, front-loaded clauses with no filler; the purpose leads. The only waste is the redundant restatement of inputs already fully covered by 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?

An output schema exists so return values need not be explained, and annotations cover side effects. What is missing is any clarification of the tariff-band behavior named in the first sentence and a fix for the phantom "fixed fee" input, leaving a user with a partially misleading picture.

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% and documents cubic_meters and price_per_m3 (with a French 2026 default), so the schema carries the load. However, the description advertises inputs as "m³ consumed, fixed fee, variable rate" — a fixed fee is not a parameter and additionalProperties is false, so an agent could try to supply a nonexistent argument. That inaccuracy pulls below the 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?

"Compute water bill from cubic meters consumed and tariff bands" is a specific verb+resource and is easily separable from the many neighboring calculators. It does not, however, contrast itself with close siblings like calculate_electricity_cost, which a one-line differentiator could have solved.

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?

"Use for household budget" implies a use case but gives no when-not guidance or prerequisites. The pointer to list_bundles for 'vie-quotidienne' calculators is the only routing hint, and it routes to a bundle lister rather than a competing tool.

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