Issue refund

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

The description goes beyond the annotations (which only indicate destructive) by disclosing the dry-run default, preview behavior, and the confirm safety gate. It also mentions the failure condition. No contradiction 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?

Two sentences, front-loaded with the action and then the safety behavior. Every word earns its place, with no redundancy or fluff.

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?

Covers the core behavior, failure condition, dry-run preview, and confirm flag. The only gap is that it doesn't describe the return value after a confirmed execution, but this is minor given the tool's simplicity and the absence of an output schema.

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 input schema already provides 100% coverage with detailed descriptions for all three parameters, including the safety semantics of confirm. The description adds no additional parameter-specific meaning beyond what the schema states, so the baseline of 3 applies.

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 specific verb+resource: 'Refund a paid invoice.' This clearly distinguishes it from siblings like update_ticket_status and extend_trial. It also adds a key precondition ('Fails if the invoice is not in paid status'), further clarifying its purpose.

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 clear context: only for paid invoices, dry-run by default, and requires confirm:true to execute. It doesn't explicitly enumerate alternatives, but the sibling tools are unrelated, so the usage context is sufficient.

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