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

Annotations already signal destructive behavior, and this description adds the specific scope of destruction ('toutes ses lignes' – all its lines) and reinforces irreversibility. This goes beyond the annotation flags by clarifying exactly what gets destroyed.

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. The first sentence front-loads the action and consequence; the second directs to the alternative without extraneous detail.

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 a single well-documented parameter, destructive annotations, and explicit guidance to an alternative, the description covers all necessary selection and invocation context. No output schema exists, but return values are not essential for this destructive action.

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% and the cartId parameter is already documented in detail in the schema (UUID, source, capability warning). The tool description itself does not add parameter information, so a baseline of 3 is appropriate.

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 uses a specific action verb ('Supprime DÉFINITIVEMENT' – permanently deletes) and a clear object ('un panier et toutes ses lignes' – a cart and all its lines). It distinguishes itself from update_cart by noting that single-line removal belongs there.

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?

Explicitly tells the agent when not to use this tool: to remove only one line, use update_cart with `remove`. This creates a clear decision rule between siblings.

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