create_refund

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the action ('Refund') but does not disclose critical behavioral traits such as whether this requires specific permissions, if refunds are reversible, potential rate limits, or what the response looks like (e.g., success/failure indicators). This leaves significant gaps for a mutation tool.

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 appropriately sized and front-loaded with the core purpose in the first sentence, followed by a specific usage rule in the second. Every sentence earns its place by providing essential information without waste.

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?

Given the complexity of a refund operation (a mutation with no annotations and no output schema), the description is somewhat complete by stating the action and parameter usage. However, it lacks details on behavioral aspects like permissions, reversibility, or response format, which are important for such a tool. It compensates partially with parameter guidance but falls short of full completeness.

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?

The schema description coverage is 0%, so the description must compensate. It adds meaning by explaining that 'payment_id' is required for refunding a payment and that 'amount' is optional (omit for full refund), which clarifies the semantics beyond the basic schema types. However, it does not detail formats (e.g., string format for payment_id) or constraints (e.g., amount must be positive).

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 clearly states the specific action ('Refund a payment') and resource ('payment'), distinguishing it from sibling tools like create_payment_preference, get_merchant_info, get_payment, and search_payments which are about creating preferences or retrieving information rather than processing refunds.

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 description provides clear context on when to use this tool (for refunding payments) and includes a usage rule (omit amount for full refund), but it does not explicitly state when not to use it or name alternatives among the sibling tools, such as when to use get_payment for checking payment status instead.

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