request_refund

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

With no annotations, the description fully discloses key behaviors: it sends an email to the operator, detects duplicate tickets, and returns existing LNURL for metered services, providing comprehensive transparency.

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 thorough but slightly verbose; however, each sentence adds value and the structure is logical with clear sections for usage and behavior.

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 or annotations, the description covers purpose, usage guidelines, parameter context, behavioral nuances, and edge cases (duplicate detection, metered service handling), making it fully complete.

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?

Adds significant meaning beyond the 100% schema coverage by explaining context (paymentId from failed call, invoice as lightning address or bolt11, optional email for follow-up, feedback max 2000 chars) and constraints not in 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?

The description clearly states the tool opens a manual 48-hour refund review ticket for a failed service (error, timeout, wrong output) and distinguishes it from automatic refunds for metered services, making the purpose highly specific and differentiated from siblings.

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 instructions on when to use (failed service) and when not to (unused-minute refunds on metered services), with alternative explanation (automatic LNURL withdrawal) and duplicate detection behavior.

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