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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavioral context: the cancellation is irreversible ('cannot be undone') and is gated on a pre-production order status, an eligibility rule absent from annotations and schema. It also names the underlying endpoint (PUT /orderCancel). It doesn't say what happens to the remaining items or order status after a partial cancel.

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, front-loaded with the 'WRITE:' severity marker, then eligibility, then call shape. Every clause carries information an agent needs and nothing is repeated verbatim from annotations or schema.

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 two-parameter destructive write with no output schema, the description covers severity, reversibility, eligibility, and parameter sourcing, which is close to sufficient. The remaining gap is the outcome of a partial cancel (resulting order/item state), which the agent must infer.

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 the baseline would be 3; the description earns an extra point by specifying that order_id is the numeric Gooten id and that order_item_ids are the OrderItemId values retrieved from gooten_get_order, giving the agent parameter provenance the schema does not. The 1-100 array bound is left to the schema, which already states it.

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 ('cancel specific items of an order') and scopes it to a subset of the order rather than the whole order. It does not explicitly name how this differs from the sibling gooten_set_order_status, which is the closest alternative for order-level changes, so it lands at 4 rather than 5.

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 a concrete eligibility precondition ('Only items of orders in a pre-production status can be cancelled') and points at gooten_get_order as the source of OrderItemId, which tells the agent how to prepare the call. It stops short of naming an explicit fallback when the order is past pre-production (e.g. set_order_status), so there is no full when-not routing.

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