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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds real value beyond them by disclosing the terminal states (CANCELED/EXPIRED) and the intermediate PARTIAL state, which tells the agent that multiple polls are expected and defines a stop condition. It stops short of stating rate limits or how to distinguish a failed token from a not-yet-created order.

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?

Two sentences, zero filler. The state sequence and the prerequisite are both front-loaded and each clause carries information an agent needs to call this correctly.

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?

An output schema exists, so return-value explanation is unnecessary, and the state machine plus token prerequisite gives the agent what it needs to invoke and interpret. The only remaining gap is the undocumented external_order_id, which slightly undercuts completeness for a two-parameter required 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 50%: status_token is documented and the description reinforces its origin ('from create_order'), but external_order_id is undocumented in both the schema and the description. Baseline 3 is appropriate since the description adds origin context for one parameter without compensating for the gap.

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 ('Poll') and resource ('order state'), and immediately enumerates the exact state machine it reports (WAITING_FOR_PAYMENT → PARTIAL → COMPLETED, or CANCELED/EXPIRED). Combined with the dependency pointer to create_order, an agent can distinguish this from validate_order and the read-only catalog siblings 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?

The word 'Poll' implies the repeat-call pattern, and the dependency 'Requires the status_token from create_order' tells the agent this is the follow-up step to order creation. It does not, however, state when to prefer this over validate_order or how often to poll, so one condition remains implicit.

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