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

Adds substantial context beyond the annotations: the call is a no-op that returns a preview plus a confirmation link, and only the merchant can carry it out. This explains why destructiveHint=false despite a 'refund' name. It stops short of describing the preview contents or error conditions.

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?

Four short sentences, front-loaded with the action, and every sentence carries non-obvious information (units, preview-only behavior, merchant confirmation). No filler.

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?

With no output schema, the description correctly compensates by describing what the call returns (a preview and a confirmation link). Combined with the schema's full parameter coverage, an agent has what it needs, though the preview payload and failure modes remain unspecified.

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 100%, so amount, restock, and orderNumber are already documented. The description's 'integer minor units (cents)' merely restates the amount schema and adds no new parameter meaning; baseline 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?

States a specific verb and resource ('Refund an order') and adds the critical money-unit convention. It does not explicitly differentiate from nearby siblings like orders_cancel or orders_lookup, but the action is unambiguous on its own.

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 conveys the workflow (agent calls, merchant confirms on the returned page), which implicitly frames when to invoke it, but it never states when to prefer this over orders_cancel or what prerequisites exist (e.g. order must be paid). Usage is implied rather than explicit.

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