Refund a transaction

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds important context: the refund is irreversible at the payment gateway, and it does not cancel subscription billing. It also reveals that the tool refuses to run without confirm: true. These details go beyond the annotations and clarify the operational impact.

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?

The description is efficiently structured: it starts with the core action, then explains irreversibility, then the non-cancellation behavior, then the confirm requirement, and finally a safety tip about checking the amount. Every sentence adds distinct value with no redundancy.

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 financially sensitive, irreversible operation, the description covers all critical aspects: purpose, irreversibility, the confirm gate, the distinction from cancellation, and a pre-call safety check. There is no output schema needed for a void action, and nothing essential is missing.

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 all three parameters (account, confirm, order_id) are already documented in the schema. The description adds no new parameter-level semantics beyond what the schema provides, such as the source of order_id or the default for account. Thus the baseline 3 is appropriate.

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?

The description states a clear verb ('Refund') and resource ('a transaction'), and explicitly distinguishes it from cancel_subscription by noting that refunding does not cancel anything. This makes its purpose unambiguous and separates it from the sibling cancellation tools.

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?

Provides explicit when-to-use guidance: refunds are for returning money, and if cancellation is intended, it says 'use cancel_subscription as well'. It also instructs to check the amount with get_transactions or get_customer before calling, and notes the confirm: true requirement. This fully covers prerequisites and alternatives.

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