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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description still adds material context the annotations cannot express: the call consumes one paid unit and never triggers a new charge. It stops short of stating idempotency — whether repeat calls with the same tx_hash consume another unit — which is the residual risk for a metered operation.

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?

Four short sentences, each carrying distinct information: purpose, alternative, inputs, side effect. The consumption warning is front-loaded alongside the purpose rather than buried at the end.

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?

There is no output schema, and the description compensates by naming the return value (the receipt). For a zero-required-parameter, metered read-or-deliver tool this covers what an agent needs to invoke it; only idempotency and repeat-call behavior are left unstated.

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 is 3. The description earns more by declaring the three identifiers are alternatives ("tx_hash, or offer_id, or intent_id"), which the schema does not encode — all three properties are optional with no oneOf/anyOf — resolving a genuine ambiguity about whether one or many are required.

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 concrete verb and outcome — deliver an already-paid resource or finish a confirming payment — plus the return value (the receipt). It also explicitly separates itself from get_checkout_status, so an agent can pick between the two without inspecting schemas.

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 the positive case (deliver a paid resource / finish a confirming payment) and the alternative with its selecting condition: use get_checkout_status to read state without consuming a unit. The distinction between consuming and non-consuming calls is exactly the decision an agent needs to make.

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