Skip to main content
Glama

BeaconMFG – China Supplier Directory

refine_sourcing

推荐轮交互。action 四选一: · best(默认)—— 按匹配度给前 3 家 + 每家一句「为什么是它」 · more —— 从本轮召回里再翻一批(value 给条数,默认 10)。不重复计费已给过的 · filter —— 追加一个约束重检(value 是要加的关键词,如「不锈钢」「ISO9001」) · details —— 看某一家在会话里的摘要(value 给 8 位 token)。要完整档案/电话请调 get_vendor:本工具只回会话里已有的字段,不额外取数。 ⚠ 名单只是初选:签约前的资质、产能、法人主体一律以 get_vendor / get_capability_card 的证据为准,不要把这里的排序当成「推荐这家」。

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": {
      "session_id": "<session_id>"
    },
    "name": "refine_sourcing"
  }
}

Input Schema

NameRequiredDescriptionDefault
valueNomore 给条数 / filter 给关键词 / details 给 token
actionNo交互类型,默认 bestbest
session_idYes会话 id(必填)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the behavioral burden, and it does disclose key traits: 'more' does not double-bill already returned items, the tool only returns fields already present in the session and performs no extra data fetching, and the ranking must not be treated as a recommendation. It does not cover failure behavior (invalid/expired 8-digit token, session not found) or latency, which keeps this below a 5.

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

Conciseness5/5

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

Front-loaded with the tool's identity, then four tight bullets, one per action, each pairing an action with its payload format and output. Every line carries operational information; the closing warning is long but materially changes how the agent should treat the output.

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 and no annotations, the description must explain return values, and it does so per action (top-3 with a one-line rationale, the next batch, a re-checked list, a session summary). It leaves gaps on session lifecycle and error cases for the token-based details path, which is a modest but real omission.

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 a baseline 3 is warranted, but the description adds real meaning: the value parameter's interpretation changes per action (count for more, keyword for filter, 8-digit token for details) and it supplies the default count of 10. The schema's own enum/description repeats some of this, so the added value is incremental rather than transformative.

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 specific interactive refinement resource (this round's sourcing recall) and enumerates the four concrete modes (best/more/filter/details) with what each returns. It explicitly contrasts itself with get_vendor and get_capability_card, so an agent can distinguish it from siblings without opening the 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?

Gives per-mode when-to-use guidance (best for top-3 match rationale, more to page through the current recall, filter to add a constraint like '不锈钢'/'ISO9001', details for a session summary by token) plus an explicit redirection: for a full profile/phone, call get_vendor instead. It also states the exclusions and caveats (ranking is not an endorsement; verify qualification with get_vendor / get_capability_card before signing).

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.