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

Goes well beyond the annotations: the cart freezes while a payment is open and after placement, quantities are clamped to stock with the response saying so, tier prices and discounts apply automatically, and op_id gives 10-minute deduplication. The conditional idempotency via op_id is an addition to idempotentHint=false rather than a contradiction, since it is scoped to a repeated id.

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?

Front-loads purpose and op semantics before moving to response shape, freeze rules, auth, and idempotency. It is dense and slightly run-on in places (the packages/pieces example, the hint sentence), but nearly every clause carries operational information.

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?

Despite no output schema, the description explains the meaningful return fields (minimum, lines[].hints, also, lines[].replacements) and their use. Auth (Bearer mo1_… or ref), the start_order prerequisite, and the frozen-cart states are all covered, which is thorough for a destructive multi-op tool.

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 already 100%, yet the description still adds meaning: the packages-vs-pieces unit rule (100 pieces of a 6-piece package is 17 packages), the link between search quantity.pieces and for_quantity, the op_id format and 10-minute replay window, and when ref is needed. This is real semantic value on top of the schema.

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 ('Change or read the order's cart') and enumerates the three op types (add/set/remove) keyed by product id, plus the read case when ops is omitted. An agent can tell exactly what the tool mutates or returns without opening the schema.

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 concrete when-to guidance: offer products/hints when it helps the shopper, ask before changing their order, and tag the accepted hint on the op. It also names cancel_payment as the way to unfreeze a cart during an open payment. It does not contrast with view_checkout/set_checkout siblings, which would be the finishing touch.

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