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

Annotations already declare readOnly=false, idempotent=true, destructive=false, openWorld=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond them: the same endpoint doubles as a read when passed only checkout_id, and the returned total depends on a delivery option having been selected. It does not mention preconditions such as order state or that the address is US-only.

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 tight sentences, front-loaded with the primary action and with the cheap re-read path stated early. The opening clause 'Choose local_delivery' is slightly jarring out of context since it omits the parameter name, and 'change ... contact details' is looser than the schema's buyer object.

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?

Return values need not be explained because an output schema exists, yet the description still usefully notes the total. For a 6-parameter tool with nested objects and only one required field, the main remaining gap is the absence of any prerequisite or state guidance (e.g. what an order must contain before a delivery option can be chosen).

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 17%, so the description must carry meaning, and it does map the mutable surfaces: quantity, delivery_address, buyer contact details, and the fulfillment_mode value 'local_delivery'. It does not cover the nested address constraints (2-letter state, US-only country, ZIP pattern) or the idempotency_key, though the schema documents the latter itself.

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 specific mutations (choose a delivery option, change quantity, address, or contact details) on a named resource and anchors it to the sibling that creates it: 'an order started with create_checkout'. An agent can distinguish this from create_checkout, complete_checkout, and get_order_status without opening any 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 explicit invocation modes: call with only checkout_id to re-read, and supply fields to mutate. It also implies the sequencing rule that the total appears only 'once a delivery option is chosen'. It does not state exclusions relative to get_order_status (read a completed order) or complete_checkout, which keeps it out of the top band.

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