Skip to main content
Glama

BeaconMFG – China Supplier Directory

suggest_filters

把一句采购口语/用户原话拆成可执行的检索参数(拆词 + 别名 + 国标类名子串),给出候选检索词与候选 gb 码,并明确「名录未收录 ≠ 这家厂不存在」。 什么时候用:search_vendors 命中偏少/为 0、或你打算凭印象猜一个国标码时。典型链路:本工具拿候选 → search_vendors(gb=) 验证 → get_vendor 取证。 ⚠ 远端轻量版:内嵌精简词表,不列全量货架、不给每类的完整条数;candidates 里的 gb 码是类名/别名推断的低置信提示,必须用 search_vendors 验证,不要直接拿它回答用户「属于某行业」。候选为空时按 next_calls 换词重试,别自己编 gb 码。 ⚠ 纯计算工具:不取企业记录,不消耗记录额度(但仍计入 IP 操作数)。

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": "suggest_filters"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNo已知城市就直接给;不给则服务端从原话里认
limitNo候选 gb 码上限 1-20
queryYes用户原话或检索词,如「找一下苏州做机加工的厂」

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so: it discloses that this is a lightweight remote lexicon version, that gb codes are low-confidence inferences from category names/aliases that must be verified, and that candidates alone must not be used to answer industry classification questions. It also specifies quota behavior — no record quota consumed but IP operation count incremented — which is exactly the kind of side-effect detail an agent needs.

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?

Well organized with explicit sections for purpose, when-to-use, workflow, and two warning blocks, with the highest-risk constraint (verify gb codes) surfaced early. It is somewhat dense and long for a three-parameter tool, but nearly every sentence carries operational information.

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?

No output schema exists, yet the description explains what comes back (candidate terms, candidate gb codes, next_calls) and how to act on an empty result, plus the quota implications. For a pure-computation helper feeding another tool, 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.

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all three parameters (query, city, limit) with examples and defaults. The description adds only modest meaning beyond that — that query is the user's raw phrasing and that city may be inferred server-side — leaving limit semantics entirely to the schema. Baseline 3 applies.

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?

States a precise verb and resource: decompose a colloquial procurement phrase into executable search parameters (word splitting + aliases + GB category substrings) and return candidate terms and candidate gb codes. It explicitly positions itself as a pre-step to search_vendors and get_vendor, so an agent can distinguish it from those siblings without inspecting schemas.

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-to-use conditions (search_vendors returns few/zero hits, or you are about to guess a GB code from memory) plus the full three-step chain: this tool → search_vendors(gb=<code>) verification → get_vendor evidence. It also states the fallback when candidates are empty (retry with different wording per next_calls) and forbids fabricating gb codes.

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.