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

Annotations are none, so the description carries the full burden. It discloses that the policy is based on public information as of a certain date and must be self-verified (未 '截至2026须自验'), and that it does not fetch real-time data (不实时抓取). This is valuable transparency about staleness and non-dynamic behavior. It doesn't mention whether it is read-only or any side effects, but as an informational tool, that's less critical. Given the explicit caveats, a 3 is reasonable; higher would require more detail on data source limitations or error handling.

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: it starts with the core purpose, then details parameters and return content, and ends with important caveats. Every sentence adds value without fluff. The structure is logical (purpose → params → return → caveats), making it easy to scan.

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 the tool's complexity (multiple platforms, multiple policy aspects) and that annotations are none, the description covers the essential: platforms, parameter values, what is returned, and data staleness caveat. An output schema exists, but the description does not rely on it; it explains the return content (return window, cost structure, etc.) without needing the output schema to fill gaps. Missing details might include specific examples or error handling for invalid platform names, but for an informational tool, this is nearly complete. A 5 would require explicit mention of what happens with invalid input or more detailed return structure.

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 0%, so the description must explain the parameter. It does: it lists the platform parameter with allowed values (amazon/walmart/ebay/tiktok_shop/shopify_dtc) and notes case insensitivity. It also explains that the return includes the platform's return window, cost structure, returnless support, and management points. This adds meaning beyond the bare schema, which only has a type and default. A higher score might include examples or default behavior clarification, but this is already strong.

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 clear purpose: comparing return policies across specific platforms (Amazon/Walmart/eBay/TikTok Shop/Shopify DTC) and providing return management points. It is specific about the resource (return policies) and the scope (platforms). While it doesn't explicitly name sibling tools, the focus on policy comparison and management guidance distinguishes it from cost calculation (calculate_return_cost) and reduction strategies (reduce_returns_playbook). A higher score would require explicit contrast with siblings.

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 when to use this tool: when you need return policy details for a platform. It doesn't explicitly state when NOT to use it or suggest alternatives. Sibling tools like calculate_return_cost and reduce_returns_playbook are not mentioned, so an agent might not know this is the policy reference tool rather than a cost or reduction tool. The usage context is clear but lacks explicit routing guidance, so a 3 is appropriate.

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