issue_refund

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

Annotations only declare readOnlyHint=false, so the description carries most of the behavioral burden — and it does well, disclosing the 30-day window, the remaining-balance ceiling, and that refunds over $100 are held for human approval rather than executed. What it omits is the observable result of a held refund (does the call succeed with a pending status or fail?), which matters 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?

Three short sentences, front-loaded with the action, followed by enforced constraints and the prerequisite call. No filler; each clause carries actionable information.

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?

For a 3-param mutation with no output schema, the agent knows the action, the hard policy limits, the prerequisite lookup, and that high-value refunds are gated. The remaining gap is what a successful versus held response looks like, but nothing prevents a correct invocation.

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%, so amount, reason, and order_id are already fully documented with format examples. The description adds only the notion that 'amount' may be partial, which is marginal. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource — refunding part or all of an order to the original payment method — which no sibling tool (get_order, escalate_to_human, etc.) shares. The scope ('part or all') is precise enough that an agent can pick this tool without inspecting the schema.

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?

Explicitly names a prerequisite sibling and action: 'Call get_order first to check amounts.' The policy block also functions as when-not guidance (over 30 days, exceeding remaining balance, >$100 requires human approval). It stops short of naming escalate_to_human as the alternative for the held case, leaving that inference to the agent.

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