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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety behaviour is covered without the description. The description adds real value beyond them by disclosing the output shape (HT, TVA, TTC over 12 and 24 months), that setup fees are separate and charged once, and that pricing is list price. It stops short of richer behavioural detail such as rounding or how the recommendation handles a custom video_hours_per_day when the profile is not visio-quotidienne.

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 content is front-loaded with purpose and output shape, then logic, then parameters, then the sibling pointer, which is a sound order. However it is delivered as a single long comma- and semicolon-chained sentence with a bare source URL appended, making it harder to scan than it needs to be. Every element is relevant but the packaging costs it.

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?

The tool is computationally complex with five parameters and a recommended-plan algorithm, and the description covers inputs, output breakdown, pricing caveats about setup fees, the underlying reasoning, and which sibling to use for a different case. An output schema exists so return values need no further explanation. It is close to complete, with only edge-case behaviour left unaddressed.

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 100%, so the schema already documents lines, days_per_month_across_border, usage_profile and video_hours_per_day in comparable detail. The description adds one genuine constraint not in the schema: all lines share the same profile, and it restates the parameter names plus the ranging rule. That is a modest addition over an already complete schema, so the baseline 3 applies.

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 resource and scope: the recommended plan and cost of a cross-border line fleet at public price, broken down into monthly HT, TVA and TTC over 12 and 24 months, with one-off setup fees shown separately. It also names the sibling it is not for mixing plans (calculate_company_price), so the tool is easy to tell apart. It falls short of a 5 because the opening is a dense noun phrase rather than a clean verb-plus-resource statement, and near-neighbours like recommend_plan or check_eligibility are never disambiguated.

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 an explicit routing rule: to mix several plans, use calculate_company_price instead. It also states the recommendation follows the rules of the questionnaire « Quel forfait ? », which tells the agent what logic drives the result. What is missing is an explicit when-not-to-use for the other calculation and recommendation siblings, so the guidance is clear but not exhaustive.

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