search_products

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

With no annotations, the description carries the full burden. It does disclose a genuine behavioral trait beyond the schema: the tool auto-paginates when limit > ~34. It does not state that this is a read-only operation, whether results are ranked/filtered server-side, or anything about errors or rate limits.

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?

Purpose is front-loaded in the first clause, which is good, but the second sentence is a long field enumeration that overlaps with the existing output schema, and the mojibake encoding ("sélectionné") degrades readability. Some of the field notes (effective_unit_price_eur, promo.min_qty interaction) do earn their place.

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 explicit field list is largely redundant; meanwhile the gaps that matter — query semantics, result ordering, and how the "selected Drive" context is established — are unaddressed. Adequate for a simple two-parameter search, but not thorough.

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 0%, so the description must compensate. The limit parameter gets meaningful treatment via the "~34" pagination threshold, but query — the required parameter — has no explanation of matching semantics (substring? fuzzy? brand names?). Partial compensation only.

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?

"Cherche des produits (prix du Drive sélectionné)" gives a specific verb plus resource and an important scope qualifier (prices come from the currently selected Drive). It does not explicitly name why you would use it versus the cart siblings, but the search-vs-mutate distinction is self-evident from the name.

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?

Usage is only implied: the closing note that product_id/offer_id/seller_id are "pour add_to_cart" hints at the search-then-add workflow. There is no explicit when-to-use/when-not statement, no guidance on query formulation, and no mention of what to do if no results are returned.

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