ebay_get_refunded_orders

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

With readOnlyHint=true already in annotations, the description reinforces this by stating 'Read-only helper' and adds valuable behavioral context beyond the annotation: it details the filtering mechanism (returns orders with non-empty paymentSummary.refunds), names the exact API invoked (getOrders), and discloses the required OAuth scope. This is consistent with the annotations and provides operational detail an agent needs before calling.

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 description is compact and front-loaded, with the core purpose in the first clause and the restrictive behavior ('Read-only helper') stated early. The appended scope requirements are useful contextual detail. It is slightly verbose with the duplicate scope statements ('Required OAuth Scope' and 'Minimum Scope'), but overall every sentence earns its place and there is no 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?

Given a simple 2-parameter tool with no output schema and readOnlyHint annotation already present, the description is quite complete: it defines the input behavior (filtering for refunds), the underlying API, the read-only nature, and auth requirements. It does not describe the return value structure in detail, but it explains what the result set is (orders with non-empty refunds array), which is sufficient for a scanning helper.

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 the schema already documents both parameters (filter with a date-range example, maxResults with default and exclusiveMinimum). The tool description does not add parameter-specific meaning beyond what the schema provides, but the overall behavioral context (scanning for refunds) helps interpret how filter and maxResults are applied. This meets the baseline for full schema coverage.

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 and resource ('Scan recent seller orders for refunds'), names the underlying API call (Fulfillment API getOrders), and precisely defines the selection criterion (non-empty paymentSummary.refunds array). It clearly distinguishes itself from siblings like ebay_issue_refund (which issues refunds) and ebay_get_orders (which fetches all orders) by scoping its purpose to refunded orders only.

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 provides clear context about when to use this tool — for scanning recent orders for refunds — and explicitly states what it does not do ('does not issue refunds or call the Post-Order API'). However, it does not name specific sibling alternatives to route the agent toward when a broader unfiltered order scan or an actual refund action is needed, leaving some selection logic to inference.

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