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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds one genuinely useful constraint — never an exact copy and never an invented SKU — which speaks to grounding/anti-hallucination behavior, but says nothing about what the call returns or how it is scoped.

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 short sentences with no filler; the criteria list is front-loaded. It is compact, though a couple of parentheticals ('famille, pas un fourre-tout') are cryptic enough to be wasted on a first read.

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?

With six optional-but-empty-defaulted parameters and an output schema present, the structure is rich, but the description still fails to convey the tool's role: it does not explain whether it is a criteria-returning reader or a filter builder feeding shopping_search, leaving the cross-tool workflow unclear.

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 parameters are already fully documented and the baseline is 3. The description adds little beyond that and actually mentions 'coupe', 'associations' and 'à éviter', which are not parameters at all, slightly muddying the mapping.

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 largely restates the name/title ('mes critères d'achat' → 'Je donne les critères') and lists attributes (matière, coupe, couleur, associations, à éviter), but the verb is ambiguous: it never says whether the tool returns criteria or accepts a criteria-filtered request, nor how it differs from the sibling shopping_search.

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?

'Critères d'abord' hints at an ordering in a flow but gives no when-to-use condition, no prerequisites, and never names an alternative such as shopping_search or recommend_look. An agent must infer routing from the schema alone.

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