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

The annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds useful behavioral context beyond that: refunds create a refund credit invoice with credit line items, money defaults to account credit unless refund_apply_order is transaction, confirmation is required by default, and the user's API key must have app access. It does not directly contradict the 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?

The refund mechanics and prerequisites are front-loaded, but the text contains some redundancy and awkward phrasing, such as repeating the line-item/whole-invoice scope and saying 'It moves money to the customer.' A few sentences do not fully earn their place, though the core information is present.

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 an 8-parameter mutation tool with no output schema, the description covers the main behavioral needs: refund methods, default credit behavior, transaction routing, confirmation requirements, feature prerequisites, and API key access. It does not describe return values or error behavior, but the absence of an output schema makes those gaps less critical.

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 the schema already documents most parameter meaning and defaults. The description still adds valuable parameter-related context by tying method choices to quantity/amount/percentage, explaining the credit-vs-transaction routing default, and noting feature gating for amount/percentage line-item refunds.

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?

Names a specific verb and resource (refund a line item or whole invoice) and immediately specifies the three supported methods: quantity, amount, or percentage. The scope (part or all of one invoice, creating a refund credit invoice) clearly distinguishes it from sibling invoice-reading tools.

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?

Gives explicit conditions for the three refund methods, states that omitting line_item_id refunds the whole invoice for amount/percentage, and names feature prerequisites for amount/percentage line-item refunds. It does not compare against sibling alternatives, but the when-to-use conditions are clear.

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