refund_htlc

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

Without annotations, the description carries full behavioral burden. It explains the refund mechanism (non-custodial, trustless, no preimage needed) and conditions. However, it omits details on idempotency or success/failure behavior beyond the parameter note for client_request_id.

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?

Description is well-structured into a title, usage conditions, parameter notes. Every sentence adds value, no redundancy. Appropriate length for the tool's complexity.

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 no output schema and moderate parameter count, the description covers usage context, parameter semantics, and behavioral intent. It lacks error scenarios or return value details, but is sufficient for an agent to invoke correctly in the stated conditions.

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% (baseline 3). Description adds value by clarifying that 'txHash' is on-chain 0x-prefixed and that 'chainType' should be 'bitcoin' or 'sui' for non-EVM legs, which is not obvious from the schema alone. Also explains 'client_request_id' as an idempotency key.

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 tool's purpose: 'Trustless unwind — recover locked funds after the HTLC timelock expires.' It distinguishes from sibling 'withdraw_htlc' by specifying when NOT to use it, providing a specific verb-resource pair and scope.

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?

Explicit 'USE WHEN' and 'DO NOT USE WHEN' sections with concrete conditions (timelock deadline passed, counterparty didn't lock) and an alternative tool named (withdraw_htlc). Also notes that only the original lock sender can call refund, and only after deadline.

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