Skip to main content
Glama

Search supplier listings

search_listings
Read-only

Search Chinese suppliers' product listings and profiles. Returns totals and the best-matching suppliers with their matching listings. Use product words only (e.g. 'bamboo cutting board'). Optional filters apply to the suppliers returned; record keeps only suppliers with a government record (FDA, import declarations naming them as maker, or a US recall), and each result's on_record lists what is on file. With hs6, makers_on_customs_record lists the companies named as the maker on customs import declarations under that code, most importers first, including makers with no supplier profile. Spends one search.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_listings"
  }
}

Input Schema

NameRequiredDescriptionDefault
hs6NoThe six-digit HS code you'd classify the product under, e.g. 853952 for LED bulbs. Give it whenever you can: it adds makers_on_customs_record, the companies named as the maker on customs import declarations for that code, including makers with no supplier profile (refs C…).
typeNo
limitNo
placeNoOnly suppliers in this province or city, e.g. 'Foshan' or 'Zhejiang'. Pass it whenever the buyer names where the factory must be, and keep the place out of query. With beyond_fair it also limits the FDA-only companies.
queryYesProduct words only
recordNoOnly suppliers with a government record of this kind: fda (FDA registration or 510(k) clearance), exports (named as the maker on import declarations), recall (a US recall), any. Use it when the question asks for proof, e.g. 'FDA-registered', 'already exports', 'verified'.
beyond_fairNoAlso list companies known only from FDA records (refs F…, no supplier profile, listings or prices) whose FDA registration names this product. place narrows them to that province or city.
certificateNoA certificate the supplier must list, e.g. BSCI, FDA, LFGB, UL/ETL, OEKO-TEX, FSC

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / beyond_fair / description
      Previous value: -"Also list companies known only from FDA records (refs F…, no supplier profile, listings or prices) whose FDA registration names this product. A place word in the query (e.g. 'catheter jiangsu') narrows them to that province or city."New value: +"Also list companies known only from FDA records (refs F…, no supplier profile, listings or prices) whose FDA registration names this product. place narrows them to that province or city."
    • addedInput schema / properties / hs6
      Added value: +{
      +  "description": "The six-digit HS code you'd classify the product under, e.g. 853952 for LED bulbs. Give it whenever you can: it adds makers_on_customs_record, the companies named as the maker on customs import declarations for that code, including makers with no supplier profile (refs C…).",
      +  "type": "string"
      +}
    • changedInput schema / properties / place / description
      Previous value: -"With beyond_fair: only companies whose FDA record is in this province or city, e.g. 'Jiangsu' or 'Suzhou'."New value: +"Only suppliers in this province or city, e.g. 'Foshan' or 'Zhejiang'. Pass it whenever the buyer names where the factory must be, and keep the place out of query. With beyond_fair it also limits the FDA-only companies."
  2. Changed2 schema fields changed
    • addedInput schema / properties / beyond_fair
      Added value: +{
      +  "description": "Also list companies known only from FDA records (refs F…, no supplier profile, listings or prices) whose FDA registration names this product. A place word in the query (e.g. 'catheter jiangsu') narrows them to that province or city.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / place
      Added value: +{
      +  "description": "With beyond_fair: only companies whose FDA record is in this province or city, e.g. 'Jiangsu' or 'Suzhou'.",
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / record
      Added value: +{
      +  "description": "Only suppliers with a government record of this kind: fda (FDA registration or 510(k) clearance), exports (named as the maker on import declarations), recall (a US recall), any. Use it when the question asks for proof, e.g. 'FDA-registered', 'already exports', 'verified'.",
      +  "enum": [
      +    "fda",
      +    "exports",
      +    "recall",
      +    "any"
      +  ],
      +  "type": "string"
      +}
  4. Changed2 schema fields changed
    • changedInput schema / properties / certificate / description
      Previous value: -"A certificate the exhibitor must list, e.g. BSCI, FDA, LFGB, UL/ETL, OEKO-TEX, FSC"New value: +"A certificate the supplier must list, e.g. BSCI, FDA, LFGB, UL/ETL, OEKO-TEX, FSC"
    • removedInput schema / properties / phase
      Removed value: -{
      -  "description": "Fair phase",
      -  "enum": [
      -    "1",
      -    "2",
      -    "3"
      -  ],
      -  "type": "string"
      -}
  5. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered; the description adds genuinely useful behavior — that the call 'Spends one search' (a cost signal) and that record keeps only suppliers with a government record while on_record reports what is on file. It does not cover result volume, ordering, or what happens when nothing matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what the tool does and returns, then layers filter semantics compactly; every clause carries information. Sentences run long and chain multiple ideas, and the 'Spends one search' cost note is buried at the end rather than surfaced early.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of describing returns (totals, best-matching suppliers, matching listings, on_record, makers_on_customs_record), which is adequate for an 8-parameter search tool. Remaining gaps are minor: no ordering/pagination info and no coverage of type, limit, or certificate behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description goes beyond it by explaining the downstream effect of hs6 (adds makers_on_customs_record including makers with no supplier profile) and the semantics of record ('keeps only suppliers with a government record'). type, limit, and certificate get no explanation in the description, but the schema covers limit minimally.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search Chinese suppliers' product listings and profiles') plus the return shape ('totals and the best-matching suppliers with their matching listings'). It does not explicitly distinguish itself from siblings like get_suppliers or find_company, which mention 'profiles' invites overlap with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage rules: product words only in query, place should be kept out of query, filters narrow the suppliers returned, and record is for proof-seeking questions. It lacks explicit when-not conditions or named alternative tools for cases where the buyer wants company-level lookup rather than listing search.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources