Search public products by keyword (name). Tìm sản phẩm công khai theo từ khóa (tên). Returns id, name, price (VND), stock, category, url.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 20, max 50). | |
| query | Yes | Keyword / từ khóa (product name). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that this is a read-only search of 'public' products and enumerates the returned fields, including VND pricing. It does not cover ordering or failure behavior, but for a simple search tool that is a minor gap.
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 English sentence is tight and front-loaded, and the return-field list earns its place. However, the Vietnamese sentence is a direct translation of the English purpose sentence, adding no new information. That redundancy prevents a higher score.
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 two-parameter search tool with full schema coverage and no output schema, the description provides sufficient orientation: scope, input, and returned fields. It lacks no call-critical information, though it omits details like ordering and output formatting.
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?
The input schema already documents both query and limit with useful descriptions, giving 100% coverage. The description only restates 'keyword (name)' and adds no parameter-specific meaning beyond the schema. Baseline 3 is appropriate because the schema carries the parameter documentation burden.
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 action ('Search'), a resource ('public products'), and a match criterion ('by keyword (name)'). This clearly separates it from siblings like get_product, list_category_products, or latest_products. The return-field list reinforces its role as a search endpoint.
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 this tool is for keyword/name-based searches of public products, but it does not explicitly state when to prefer it over alternatives or when not to use it. Usage context is present, but alternative routing is left to inference.
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.
Product discovery tools such as best_sellers, latest_products, recommend_products, and similar_products have related listing purposes and could be confused, though descriptions clarify sorting and filtering criteria. Social-check tools also overlap: check_live_facebook, deep_inspect, and check_health_bulk can all verify Facebook accounts. Most tools are distinct, but the boundaries are not always crisp.
The dominant convention is snake_case verb_noun, e.g. buy_product, search_products, list_categories, check_order_status. A few names deviate, such as best_sellers, latest_products, similar_products, how_to_start, and deep_inspect, but they are still readable and predictable.
With 19 tools, the set falls into the 16-25 heavy range and could be trimmed: there are nine product-listing/search/recommend tools and three overlapping social-check tools. The count is not extreme, and the combined commerce-plus-verification scope is covered, but it feels heavier than necessary.
The core commerce workflow is complete: discover products, quote, confirm purchase, check order status, and view balance. Minor gaps include no order-history tool, no cancellation tool, and no actual top-up execution, but these are workaroundable for the stated shop purpose.