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

Adds genuinely non-obvious behavior beyond the annotations: the call is a no-op preview returning a confirmation link, and only the merchant on that page can actually apply the change. This materially reframes how the agent should treat the result. It stops short of saying what the preview contains, what happens if a confirmation is never used, or what happens with multiple parcels beyond the `find` parameter.

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 sentences, purpose front-loaded, no filler in the first and third. However the middle sentence about money in minor units earns nothing for this tool and dilutes an otherwise tight definition.

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 mutation-adjacent tool with annotations and no output schema, the description covers the critical unknowns: no state change occurs on the call and the return is a preview plus confirmation link. The stray money sentence is the main defect; permissions and multi-parcel edge cases are adequately handled by the schema.

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 baseline is 3, but the only semantic content the description adds is "Money is integer minor units (cents)" — this tool has no money parameter, so that sentence is inapplicable and risks making an agent hunt for a price field that does not exist. The `find`/`delivered`/`orderNumber` semantics are left entirely to 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 ("Mark a parcel as delivered") and immediately scopes it further by revealing that the call itself only produces a preview. An agent can distinguish it from orders_fulfil or orders_update_shipment by the parcel-level delivered mark, though no sibling is named explicitly.

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?

Implied usage only: the description tells you the merchant must complete the action on a confirmation page, which signals you cannot finish the job with this tool alone. It never says when to prefer this over orders_fulfil, orders_update_shipment, or orders_remove_shipment, so routing between the order-mutation siblings is left to inference.

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