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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful semantics beyond that: no stock is reserved by the read, and the business qualification of the fiche is kept separate from the offer state.

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 tight sentences: the first front-loads the core action and the field set, the second adds the non-reservation caveat. No filler, though the enumerated field list is dense enough to read as a run-on.

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 return shape need not be explained, and annotations carry the safety profile. The description supplies the domain semantics an agent needs (point-in-time snapshot, no reservation, distinct availability vs authorization); only an explicit pointer to sibling tools is missing.

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?

With a single parameter at 100% schema description coverage, the schema already documents product_id (internal PID, bounds, pilot PID1843 caveat). The description adds nothing further about the parameter, so the baseline of 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?

States a specific verb and resource ('Lire l'offre canonique') and enumerates what the read exposes (mise en vente, stock compté, disponibilité, autorisation de commande). An agent can distinguish it from get_product because it is scoped to the commercial offer rather than the catalog record, though no sibling is named explicitly.

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?

Gives clear context for calling it: a point-in-time ('à l'heure d'observation') read that separates availability from order authorization. The note that it reserves no stock implicitly routes reservation/ordering intent to create_order or quote_cart, but no alternative tool is named outright.

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