搜尋台灣電商商品與價格（涵蓋 momo、PChome 24h 與台灣品牌官網）。回傳商品名、目前價格、通路與購買連結，依價格由低到高。使用者想買某商品、問價格、要推薦選購時使用。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 回傳筆數，預設 10，最多 20 | |
| query | Yes | 商品關鍵字，例如「藍牙喇叭」「氣炸鍋」「Marshall 喇叭」 | |
| channel | No | 限定通路：momo｜pchome｜official（品牌官網），可選 | |
| max_price | No | 價格上限（元），可選 | |
| min_price | No | 價格下限（元），可選 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. It states return fields and sorting behavior ('依價格由低到高'), implying a read-only search. It does not explicitly disclose idempotency or safety, but the semantics are clear enough for a search tool.
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?
Three sentences: what it does, what it returns, when to use. No wasted words, front-loaded with essential information.
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?
No output schema, but description explains return structure (product name, price, channel, link) and sorting. It covers all key aspects for a search tool, though pagination or limit behavior could be mentioned.
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 parameter descriptions are clear. The tool description adds context about result sorting (by price low to high) not in schema, but otherwise does not add meaning beyond schema. Baseline 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 ('搜尋'), resource ('台灣電商商品與價格'), and scope ('涵蓋 momo、PChome 24h 與台灣品牌官網'). It distinguishes from siblings by focusing on cross-channel product search for Taiwan e-commerce, unlike compare_prices or find_deals.
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 explicitly says when to use ('使用者想買某商品、問價格、要推薦選購時使用'). It provides clear context but does not mention when not to use or alternatives among the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, such as price comparison vs. price history vs. store safety. However, there is some overlap between compare_prices, cross_channel_gaps, and price_match_check, which all involve comparing prices across channels. The descriptions help differentiate them, but ambiguity remains for agents.
Tool names use snake_case but vary in structure: some start with verbs (compare_prices, find_deals), others with nouns (category_price_range, price_match_check). There is no strict verb_noun pattern, and 'should_i_buy_now' is a full phrase, breaking consistency.
17 tools cover a wide range of e-commerce assistance tasks without being overwhelming. The count is appropriate for the domain, though a few tools (e.g., price_match_check vs. should_i_buy_now) could potentially be merged without losing functionality.
The tool set covers most common user needs in Taiwanese e-commerce: product search, price comparison, historical trends, deals, store safety, tech detection, and currency conversion. Missing operations include user-specific features (e.g., watchlist) but the core lifecycle is well-represented.
