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

Annotations only declare readOnly and idempotent; the description adds substantial behavior: results are grouped per shipping profile and zone, fees are in minor units, and failures surface as explicit null reasons (id_check, currency, weight_missing, too_heavy, over_bands). It also discloses two non-obvious rules — age-restricted products require an ID-checking carrier, and the quoted fee is not the final charged amount — which an agent could not infer from the schema or annotations.

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?

The definition is front-loaded with the core purpose and its parenthetical nature, and the enumerated failure codes are densely packed rather than padded. It is a little overstuffed in a single long sentence, but almost every clause carries information an agent needs.

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 does the return-shape work itself: per-profile zone assignment, each service with its fee, the null-reason enumeration, and the separate 'unquoted' set for non-shippable or unpriced products. For a read-only, two-parameter tool that is enough for an agent to interpret the response without guessing.

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 effectively 0% (only the nested region field carries a description), and the description does not explain the top-level inputs 'lines' or 'destination' beyond the narrative words 'basket' and 'place'. It gives no guidance on what a valid product_id is, why lines are capped at 50, or how postal_code versus region changes the result, leaving the nested-object parameters under-specified.

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 ('what shipping a basket to a place costs') and pins the scope ('by the business's own rate tables'), with the parenthetical 'a read, never an order' distinguishing it from order-creating siblings like create_order and request_quote.

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?

'a read, never an order' gives a clear inclusion/exclusion signal about when this is appropriate versus committing a purchase. It does not, however, name the sibling it should be paired with (e.g. request_quote) or state prerequisites such as whether the products must belong to the same business, so it stops short of explicit routing.

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