Skip to main content
Glama

BeaconMFG – China Supplier Directory

search_vendors

检索灯塔名录里的中国各行业经营主体(GB/T 4754 全门类,21 万家)。可按关键词(企业名/品牌/工艺/材料/认证/服务内容)、城市或区县、国标小类码过滤。返回精简档案,字段名是短名:id/token(8 位,传给 get_vendor 与 get_capability_card)、co(企业名称)、city(城市)、dist(区县)、gb(国标小类码)、proc(工艺)、mat(材料)、cert(认证)、has_phone(是否有电话)、tel(1=含电话,兼容旧客户端)、cap(能力键)、products(产品词)、lat/lng(坐标)。⚠ 检索结果不含电话号码:号码是一条一个额度的取证动作,请用 get_vendor(id);工艺证据档位在 pinf:省缺或 null=有事实工艺;A1~B0=零采集推断(分档非核实);class_default=挂的是国标小类默认工艺码,不是这家企业的事实工艺,严苛场景请降权。⚠ 关键词是字面子串匹配:口语词与归档写法不同会漏(「机加工」vs「机械零部件加工」)。0 命中时不要直接答「没有」—— 换同义词重试,或改用 city+gb 定向。 ⚠ 技术/能力词(「人工智能」「五轴加工」)在国标里可能根本没有对应小类;这种情况用 cap=<能力键>(suggest_filters 的 cap_candidates 会给)按能力索引定向,别硬塞进 query 做字面 AND,也别把 cap 当成 gb 码。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_vendors"
  }
}

Input Schema

NameRequiredDescriptionDefault
gbNo国标小类码,如 3484(机械零部件加工)、6210(正餐服务)。给了就只扫对应分片,召回与速度都更好
capNo能力键定向,如 tech_ai / cnc_turning;来自 suggest_filters 的 cap_candidates[].cap,**不是国标码**(最多 6 个用 caps)
gbsNo多个国标码一次定向(最多 6 个),比逐码调用省 RTT 与额度
capsNo多个能力键一次定向(最多 6 个)
cityNo城市名,如 深圳 / 东莞 / 苏州;也接受区县或县级市(昆山、海盐)。**省名不是合法取值**
limitNo返回条数上限 1-200
queryNo关键词:企业名/品牌/工艺/材料/认证/服务内容子串。词表认得的品类词(兰花 / 医院 / 人工智能…)会自动带能力域加权,回执里有 cap_auto
offsetNo分页偏移

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"关键词:企业名/品牌/工艺/材料/认证/服务内容子串"New value: +"关键词:企业名/品牌/工艺/材料/认证/服务内容子串。词表认得的品类词(兰花 / 医院 / 人工智能…)会自动带能力域加权,回执里有 cap_auto"
  2. Changed3 schema fields changed
    • addedInput schema / properties / cap
      Added value: +{
      +  "description": "能力键定向,如 tech_ai / cnc_turning;来自 suggest_filters 的 cap_candidates[].cap,**不是国标码**(最多 6 个用 caps)",
      +  "type": "string"
      +}
    • addedInput schema / properties / caps
      Added value: +{
      +  "description": "多个能力键一次定向(最多 6 个)",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / city / description
      Previous value: -"城市名,如 深圳 / 东莞 / 苏州;也接受区县或县级市(昆山、海盐)"New value: +"城市名,如 深圳 / 东莞 / 苏州;也接受区县或县级市(昆山、海盐)。**省名不是合法取值**"
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: results exclude phone numbers because a number is a one-per-quota evidence action, pinf grades (null = evidenced process, A1~B0 = zero-collection inference, class_default = taxonomy default not this firm's fact) are disclosed with a warning to downweight in strict scenarios, and keyword matching is declared literal substring.

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-loaded with purpose and filters, then caveats marked with ⚠, so an agent can skim. It is dense and the field-by-field glossary is long, but since there is no output schema that block is load-bearing rather than filler.

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

Completeness5/5

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

For an 8-parameter, zero-required search with no output schema and no annotations, the description covers return shape, quota economics, evidence-quality caveats, and failure recovery. Nothing an agent needs in order to call it correctly is missing.

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 100%, so baseline is 3, but the description adds real semantics beyond the schema: query is a literal substring match where colloquial words miss archived phrasings, cap keys are not GB codes and must not be mixed into query, and query vocabulary hits return cap_auto. It also explains the short field names in the response that the schema cannot.

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

Purpose5/5

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

Opens with a specific verb+resource and scope: retrieving Chinese business entities from a directory covering the full GB/T 4754 taxonomy (210k records), filterable by keyword, city/district, or GB subclass code. It also separates itself from the sibling get_vendor by stating that phone numbers come only from get_vendor(id).

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

Usage Guidelines5/5

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

Gives explicit when/when-not rules: on 0 hits do not answer 'none' — retry with synonyms or switch to city+gb; for technical/capability terms that have no GB subclass, use cap= from suggest_filters' cap_candidates instead of forcing them into query as a literal AND. It also names get_vendor as the alternative for phone data.

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.