Skip to main content
Glama

Trustbase Lab · Trusted Data Infrastructure for the AI Era

by com.trustbaselab
OverviewDiscussionsAdmin

Search Companies & Capacity Projects

query_companies
Read-onlyIdempotent

Purpose: query the global rCB company and project database (132 records: domestic / international / equipment vendors) by segment, region, status and keyword - the discovery tool for capacity projects and players in the chemical recycling industry. Guidelines: combine segment (rcb/virgin/conductive) + status ('在建','规划','under construction') + location; for capacity-project lists filter status, then pair with get_company for full entity detail. Limits: company-level records only - capacity is a record attribute, not a separate projects table; confidence varies A/B/C. Ex: 'rCB projects under construction in China', 'conductive carbon black producers worldwide'.

Input Schema

NameRequiredDescriptionDefault
groupNo数据分组：all=全部（默认）, domestic=中国国内, international=国际, vendors=设备厂商
limitNo返回条数上限（默认 20，最大 100）
offsetNo起始偏移，默认 0；返回体 has_more=true 时用 next_cursor 作为下一页 offset
regionNo区域过滤（与 group 等价，兼容 AI Agent 习惯）
statusNo状态关键词，如 '在运'、'新建'、'在建'、'规划'
keywordNo企业名或产品线模糊匹配，如 '炭黑'、'pyrolysis'
segmentNo业务板块过滤（schema 1.6 基准层）：rcb=再生炭黑业务, virgin=原生炭黑基准厂商, conductive=导电特种炭黑
languageNo输出语言：zh=中文（默认）, en=英文zh
locationNo地点/国家关键词，如 '山东'、'德国'
verifiedNo是否 Verified Supplier：true=只看 A 级可信供应商（AI Agent 推荐用）
confidenceNo置信度：A=政府文件核实, B=企业自述/权威媒体, C=待核实
response_formatNo输出格式：markdown=人类阅读（默认）, json=Agent 处理友好markdown

Output Schema

NameRequiredDescriptionDefault
textYesHuman-readable result (markdown, or a JSON string when response_format=json).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "起始偏移，默认 0；返回体 has_more=true 时用 next_cursor 作为下一页 offset",
+  "type": "integer"
+}
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "text": {
+      "description": "Human-readable result (markdown, or a JSON string when response_format=json).",
+      "type": "string"
+    }
+  },
+  "required": [
+    "text"
+  ],
+  "type": "object"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / segment
      Added value: +{
+  "description": "业务板块过滤（schema 1.6 基准层）：rcb=再生炭黑业务, virgin=原生炭黑基准厂商, conductive=导电特种炭黑",
+  "enum": [
+    "rcb",
+    "virgin",
+    "conductive"
+  ],
+  "type": "string"
+}
  4. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description goes beyond them by disclosing dataset size (132 records), a confidence tiering scheme (A/B/C), and a structural limitation about capacity being a record attribute rather than a projects table. It stops short of describing pagination or result-shape behavior, but the offset/has_more semantics live in the schema.

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?

Labelled sections (Purpose / Guidelines / Limits / Ex) make it skimmable and front-loaded, and each sentence carries usable information. It is denser than strictly necessary and mixes English prose with Chinese enum literals, but there is no filler or repetition of schema content.

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 a 12-parameter discovery tool with an output schema present, the description supplies everything the agent needs to call it correctly: dataset scope, filter-combination strategy, a hand-off to get_company, confidence semantics, and example queries. Return-format details are legitimately delegated to the output schema.

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 baseline is 3 and the per-parameter descriptions carry the burden. The description still adds value over the schema by explaining how parameters should be combined (segment + status + location) and by mapping example queries to concrete filter sets, which the schema alone does not convey.

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 verb and resource ('query the global rCB company and project database'), names the dataset scope (132 records: domestic / international / equipment vendors), and positions itself as 'the discovery tool for capacity projects and players'. It explicitly routes the agent to get_company for entity detail, so it is distinguishable from its sibling without opening either 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 concrete when-to-use guidance ('combine segment + status + location; for capacity-project lists filter status, then pair with get_company') plus two worked examples that map directly onto parameter combinations. It also states a boundary (company-level records only, capacity is an attribute not a separate table), which prevents the agent from expecting a projects table.

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

All Trustbase Lab · Trusted Data Infrastructure for the AI Era toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources