Skip to main content
Glama

BeaconMFG – China Supplier Directory

start_sourcing

多轮寻源起手:把一句自然语言需求(「找东莞做注塑代工的,最好有 ISO9001」)变成一轮定向检索 + 1~2 个只问必要信息的澄清问题,返回 session_id 供 answer_sourcing / refine_sourcing 续接。 什么时候用它:用户有采购/代工/找厂意图,但需求还含糊(没说城市、没说工艺类别)——这种需求直接 search_vendors 会拉回一堆跨行业噪声。 什么时候别用:需求一句话就能答(「东莞注塑厂有哪些」)→ 直接 search_vendors,省一次会话和一轮额度。 返回:stage(no_recall / clarifying / shortlist)、recalled(本轮取回家数)、clarifying_questions(每条带 field + options,options 的取值直接来自候选集,答了就能用来过滤)、preview(前 3 家)。 ⚠ 澄清问题最多 2 轮,且只问「答了能过滤」的字段(城市/工艺/认证)——交期、数量这类名录里没有的字段一律不问,问了也做不到。 ⚠ 会话 2 小时过期,且只在同一出口 IP 下可取回(纯 IP 身份,不认 API key);换网络/换代理后 session_id 会变成「不存在」。

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": {
      "demand_text": "<demand_text>"
    },
    "name": "start_sourcing"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNo已知城市就直接给,省掉一轮澄清
limitNo本轮取回家数 1-50(每家算 1 条额度)。默认 20,够做初步筛选
demand_textYes一句话需求:品类/工艺/材料/地区/认证,越具体越好

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

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: it discloses the returned stage enum, that options come from the candidate set, that clarification is capped at 2 rounds, that only filterable fields are asked, and that sessions expire in 2 hours and are bound to the exit IP (not API key) so session_id dies on network change. These are non-obvious operational constraints an agent could not infer elsewhere.

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 the core action, then organized under labeled sections (when to use / when not / returns / ⚠ caveats), which makes it scannable. It runs long and repeats the noise-point twice, but nearly every sentence carries decision-relevant information for a stateful multi-round tool.

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 and no annotations, yet the description covers return fields (stage, recalled, clarifying_questions, preview), the clarification policy limits, and session lifecycle/auth model. For a session-creating tool of this complexity, an agent has everything needed to call it and to know when its session will break.

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 the per-parameter descriptions already explain city/demand_text/limit. The description adds meaning beyond the schema by tying limit and demand_text to the quota model ('每家算 1 条额度', '省一次会话和一轮额度') and by explaining why supplying city matters (it removes a clarification round). Not full syntax detail, but genuine added semantics.

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?

Names a specific verb+resource (多轮寻源起手) and states its concrete transformation: a free-text demand becomes one retrieval round plus 1–2 clarifying questions, returning a session_id. It explicitly contrasts with search_vendors ('直接 search_vendors 会拉回一堆跨行业噪声'), so the agent can distinguish it from siblings without opening any schema.

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?

Provides explicit 什么时候用它 (vague procurement intent, missing city/process) and 什么时候别用 (single-sentence answerable demand → search_vendors), plus names the continuation tools answer_sourcing / refine_sourcing. Both the positive and negative conditions are stated, which is the top bar for this dimension.

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.