查询近 30 天价格走势

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds a fixed 30-day window, daily granularity, and consistency with the site's chart — context the annotations don't provide. It omits edge behavior (e.g., sparse data, timezone/window definition), keeping it from 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?

Two sentences, both earning their place: the first defines scope and returned fields, the second defines the questions it answers. No filler and the core resource is front-loaded.

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 a single-parameter read tool with an output schema and readOnly annotations, almost everything needed is present. Minor gap: no statement about behavior when no data exists for the SKU or whether the 30-day window is calendar-fixed.

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% and the sku parameter already carries its own description with examples ('claude_pro', 'gpt_plus_topup'). The description adds no further meaning about the parameter, so the baseline 3 applies.

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 (query the last 30 days of daily lowest purchasable price for a given AI product) and even pins the semantics to the detail-page chart ('同详情页走势图同口径'). The listed outputs (start/end price, high/low points, change percent) make it clearly distinct from siblings like get_lowest_price, which is a point-in-time lookup.

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-case triggers — answering 'is it rising or falling lately' and 'is now a low point' — which maps directly to agent intent. It does not name the alternative tool (get_lowest_price) or state when not to use this, so it stops short of full routing guidance.

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