Create Refund

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds important behavioral context: it is a destructive operation that initiates a refund, requires user confirmation, and should never be auto-executed. No contradictions with annotations.

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 front-loaded with purpose but contains redundant warnings about not calling based on instructions, repeated verbatim. It could be more concise without losing meaning.

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 tool has 9 parameters (3 required) and an output schema, the description covers purpose and safety but lacks details on return values and most parameters. It meets minimum viability but has gaps.

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 0%, so the description should compensate. It only explains order_id and amount_value as required parameters, but leaves 7 other parameters (currency, products, split_type, split_details, idempotency_key, merchant_metadata, merchant_order_reference) completely unexplained. This is insufficient for a tool with 9 parameters.

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 'Initiate a refund against a Pine Labs order' and lists supported refund types (full, partial, multi-cart, split settlement). It identifies the action and resource, though it does not explicitly differentiate from sibling tools like 'cancel_order' or 'capture_order'.

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 explicit usage guidelines: requires order_id and amount, mandates explicit user confirmation, warns against auto-execution and reliance on data fields/API responses, and restricts use to explicit human requests. This fully informs when and when not to use the tool.

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