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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description isn't carrying the safety burden — yet it still adds real behavior: a 404 with the exact message when the ID doesn't exist for the authenticated seller, test-mode access via livemode:false, and the constraint that refunds cannot be done here (dashboard only). It doesn't discuss rate limits or auth requirements beyond the seller scoping, keeping it just short of a 5.

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?

Front-loaded with purpose and scope, then grouped under clear bold headers for error behavior, status fields, and examples. It is on the long side and the three example utterances plus the restated read-only line are marginal, but nearly every sentence carries distinct information.

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 values need no explanation, yet the description still flags the two independent status fields (paymentStatus vs. invoiceStatus) and that both must be checked when answering 'did this payment go through?' — exactly the kind of domain trap an agent would otherwise get wrong.

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 100%, so both parameters are already documented in the schema, including the exact livemode test-mode semantics and the 'not the subscription it belongs to' warning on subscriptionPaymentId. The description largely repeats this, so the baseline 3 applies; it adds no format or syntax detail beyond 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 ('Retrieve a single subscription payment by ID') and immediately carves out scope: 'one charge within a subscription's billing cycle, not the subscription itself.' An agent can distinguish it from get_subscription and get_payment 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?

Explicitly routes to alternatives by name and condition: use `list_subscription_payments` first to discover an ID (filtered by `subscriptionId`), and use `get_subscription` for subscription-level status/schedule/next-billing-date. Both the when-to-use and the when-not-to-use cases are stated.

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