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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses meaningful behavior: nothing is committed, the total is pre-tax (hors TVA et port), prices are frozen at add time, and the full cart is returned. It adds real context on side-effect semantics and pricing, though it does not cover auth/rate-limit specifics beyond implying anonymity.

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?

Four dense sentences, front-loaded with the core action and immediately followed by the highest-value caveats (not an order, frozen prices, required inputs, return behavior). No filler; every clause carries an operational instruction.

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 no output schema, the description correctly compensates by stating the return value ("Renvoie le panier complet") and warning against a redundant follow-up call. Combined with the annotations and 100%-covered schema, an agent has everything needed to invoke it correctly.

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 100%, so baseline is 3, but the description adds cross-parameter meaning: each line requires productId AND sku, both sourced from search_products, which is a dependency the schema alone does not state. It reinforces rather than replaces the already rich per-field schema text.

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 ("Crée un panier anonyme"), adds scope (anonymous) and optional initial lines, and explicitly distinguishes the artifact from a sibling concept ("Un panier n'est PAS une commande"). An agent knows exactly what is produced and how it differs from an order.

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: use it to start a cart, optionally seeded with lines, and it names the anti-pattern to avoid ("n'appelez pas get_cart juste après") plus the prerequisite source for inputs (search_products). It does not, however, contrast with update_cart for the case of adding lines to an existing cart, so no explicit alternative routing for that decision.

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