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

Annotations already declare this is a safe read-only, idempotent, non-destructive calculation. The description adds useful behavioral context beyond annotations: it explains that SIM/eSIM one-time fees are given separately, that delivery is included, and that it indicates whether online subscription is open. It does not contradict the 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?

The description is front-loaded with the core calculation and usage examples, and every sentence adds practical context. It is a bit dense and includes a source URL that is less essential for invocation, but overall it is appropriately structured.

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 the description need not document return values in detail. For a three-parameter pricing calculator, the description covers the calculation, input meaning, fee handling, and online-subscription status, which is complete enough for correct selection and invocation.

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%, so each parameter is already documented as a line count for a specific plan. The description adds meaning beyond the schema by explaining that plans can be mixed and that each count is 0–20, with more than 20 total lines handled by request at the same price.

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 states a specific calculation: monthly cost (HT, TVA, TTC), 12/24-month HT pricing for a fleet at public price, mixing plans if needed. It is clearly distinguishable from siblings such as calculate_cross_border_fleet, compare_plans, or get_plans because it computes a fleet price from line counts.

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?

It explicitly gives when-to-use examples: « combien pour 5 lignes ? » and « combien pour 3 Pro et 2 Business ? ». It also states the boundary condition that beyond 20 total lines the order is by simple request at the same price, which tells the agent when the tool's normal input range is no longer the whole story.

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