get_refund_summary

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

No annotations are provided, so the description carries the full burden. The description clearly discloses the read-only nature (a 'get' tool) and the performance implication in the start_date parameter description, warning that the tool scans every order in the range. However, it does not disclose details about return value structure, pagination, or potential limitations (e.g., whether refund rates are based on orders or items), which prevents a 5.

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 main description is a single, focused sentence that enumerates the key outputs in a structured list. The parameter descriptions are also concise yet informative. Every word adds value, and the overall structure is clean and easy to parse.

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 no output schema, the description compensates by listing the main return metrics (refund amount, count, rate, item details) and mentions the net revenue support. The performance warning is helpful. However, it lacks a breakdown of the returned items structure and does not clarify how this tool relates to nearby siblings like get_refund_by_store, leaving some ambiguity for the agent.

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%, meaning both start_date and end_date have descriptive text in the schema. The main description adds no additional parameter information, but the schema descriptions themselves are detailed, including a warning about query scope. Since the schema already does the heavy lifting, a baseline of 3 is appropriate.

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 ('取得' meaning 'get') and resource ('退貨退款統計' refund/return statistics) with a clear scope (指定時間區間, a specified date range). It enumerates concrete outputs: refund amount, number of returns, return rate, and returned item details, which distinguishes it from sibling tools like get_refund_by_store or list_return_orders.

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 implies usage for obtaining aggregate refund metrics over a time range, but it does not explicitly contrast with alternatives such as get_refund_by_store or get_return_order_detail. Parameter descriptions provide advice about using short date ranges for performance, which is a form of when-to-use guidance, but there is no explicit exclusion or alternative recommendation.

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