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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered elsewhere. The description adds one genuinely useful behavioral detail — that the location filter matches ANY of a customer's addresses — but says nothing about pagination limits or result shape, so it is merely additive rather than rich.

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?

Two sentences, no filler, with the capability statement front-loaded and the use case trailing it. The list of filter dimensions is long but each item is a distinct capability, so it earns its space.

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 14-parameter filter tool with 100% schema coverage and an output schema, the description covers purpose, filter axes and a use case adequately. It omits any mention of pagination behavior or default/max result limits, which the schema carries but the agent might benefit from seeing alongside the capability summary.

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%, including enum values for sort, so baseline is 3. The description helpfully groups the semantic axes (location, spend, order count, recency, unpaid) without adding syntax or format detail beyond the schema, which already documents every parameter.

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+resource ('Recherche des clients') and enumerates the searchable dimensions (nom, e-mail, société, lieu, nombre de commandes, montant dépensé, ancienneté, impayés), which lets an agent distinguish it from the single-record get_customer sibling. It does not explicitly name any sibling, so it falls short of a 5.

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 second sentence supplies one concrete use case ('cibler une relance commerciale'), which implies when the tool is appropriate. However, there is no explicit when-not guidance and no named alternative (e.g. list_unpaid_orders for unpaid-only queries), so usage remains inferable rather than stated.

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