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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: it requires a meta["idempotency-key"] UUID for retry safety (explaining how to make a non-idempotent destructive call safely) and states the auth requirement via cart_access_token from create_cart. It stops short of saying what happens to an already-cancelled cart or whether cancellation is reversible.

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?

Three short sentences, zero filler, with the action and its identifiers front-loaded followed by the retry-safety requirement and the scope exclusion. Every sentence carries distinct 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?

For a three-parameter destructive mutation with no output schema, the description covers identifiers, the idempotency contract, and the domain boundary. Missing only the return shape and the behavior on repeated/already-cancelled calls, which are minor for an agent to proceed.

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 only 33% (only cart_access_token is documented), so the description must compensate and largely does: it identifies `id` as the cart id, `cart_access_token` as the owner token, and specifies that the otherwise-opaque `meta` object must carry an idempotency-key UUID. The remaining gap is that `meta` is a free-form nested object and only one key is documented.

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?

Names a specific verb (cancel) and resource (Shopify-owned cart) and scopes it to carts the platform owns, which separates it from the order/refund domain. It does not explicitly name the sibling alternatives (get_cart, update_cart, create_cart), but the verb alone makes the intent unambiguous.

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?

The closing sentence gives a useful exclusion ("does not cancel an order or refund payment"), which steers agents away from order-cancellation tasks. However, it never says when to reach for cancel_cart versus update_cart or get_cart, nor what precondition (e.g. cart still active) must hold.

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