Find Alibaba supplier / manufacturer listings for a query (via Serper site:alibaba.com) — returns title + rating + a supplier snippet + the Alibaba link. TEXT ONLY: no price or photo are available via this source (the user sees price / MOQ / photos on Alibaba after clicking).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The product / OEM query (brand-free for private label). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description clearly states the result is TEXT ONLY and explicitly warns that price and photo are not available, with a note that the user sees them after clicking the Alibaba link. It also names the exact return fields, which is valuable behavioral context.
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 with no wasted words. The main action and source are front-loaded, followed by a compact list of return fields and a clear limitation note. Every sentence adds value.
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?
The tool has one parameter, no output schema, and read-only annotations. The description sufficiently covers what the tool returns, what it does not return, and the source. An agent has enough information to call it correctly and set user expectations.
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 query parameter already includes a helpful description about being brand-free for private label. The tool description adds no extra parameter meaning beyond that, so the baseline score 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?
Description uses a specific verb ('Find') with a concrete resource ('Alibaba supplier / manufacturer listings') and a scoped mechanism ('via Serper site:alibaba.com'). It clearly distinguishes itself from generic search tools by focusing on Alibaba supplier results and listing exactly what is returned.
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 its usage context: finding Alibaba supplier listings for a product/OEM query. However, it does not explicitly state when to use this tool over alternatives like web_search, search_products, or shopping_search, nor does it give a when-not-to-use condition.
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.
The tool set is extremely granular, with multiple clusters that overlap in purpose (e.g., amazon_search_results/search_products/shopping_search; watchlist_delta/watchlist_diff; find_undercompeted_brands/category_undercompeted_brands; operator_new_brands/operator_new_on_brand). Although descriptions are detailed, the boundaries between many 'find opportunity' and 'watchlist change' tools are subtle enough that an agent could easily misselect.
The vast majority follow a verb_noun snake_case convention with clear prefixes (asin_, brand_, category_, operator_, watchlist_, playbook_, find_, top_). A few noun-style exceptions (competitive_landscape, risk_assessment, brand_under_attack, buybox_loss_alert) break the pattern, but they are minor and do not obscure the overall scheme.
With 82 tools, the server is far beyond the 50+ extreme threshold. Even though the domain is broad, many tools are highly granular variants (e.g., filter_brands_by_fba_share vs filter_operators_by_fba_share; watchlist_delta vs watchlist_diff) that could be merged or parameterized, imposing a heavy cognitive and context burden on agents.
The surface is extraordinarily complete for Amazon product research: discovery, ASIN/brand/category analytics, buybox and BSR history, sourcing evaluation, risk/MAP monitoring, watchlists, playbooks, operator intelligence, cross-marketplace checks, and live refreshes. Workflows like authorized_seller_set → buybox_loss_alert and watchlist_add → watchlist_delta are fully supported, with no obvious dead ends.
