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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is low, but the description goes further with a pricing model: ¥0.1 per call, billed only on success, with automatic refund on failure or empty results. That cost/failure semantics is decision-relevant information an agent cannot get from any structured field, and it also lists the returned data categories in the absence of an output schema.

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?

Front-loaded with the purpose and a parenthetical scope caveat, followed by return fields, use cases, and billing. Every sentence carries information, though the return-field enumeration is dense and could be more scannable. No filler or repetition.

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 compensates by enumerating returned fields, and it adds cost and refund behavior plus intended use cases. Minor gaps remain: it does not say whether Tmall listings are covered (only the annotation title mentions 淘宝/天猫) or mention the header-token auth preference noted in the schema.

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% with only two parameters (item_id and optional _token), and the schema already documents both, so the schema carries the burden. The description adds no format, ID-source, or fallback guidance for item_id or _token. Baseline 3 applies when the schema fully documents the inputs.

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 (fetch Taobao pre-coupon item detail) and enumerates what the response contains (title, price/discounts, SKU specs, sales, shop info, main/detail images, stock). It also scopes itself negatively by excluding post-coupon price, coupon face value and commission, which hints at what it is not. It never names the overlapping siblings (taobao_item_get, taobao_item_desc), so an agent still has to infer which Taobao detail tool to pick.

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 concrete use cases (single-item price monitoring, inventory comparison) and a usage restriction (recommended mainly for title/image retrieval). There is mild tension between 'use for price monitoring' and 'use only for title/images', and no named alternative tool is offered for the coupon-inclusive case. Still, clear situational context that most sibling definitions lack.

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