Trustbase Lab · Trusted Data Infrastructure for the AI Era

Search Industry Articles

query_articles

Read-onlyIdempotent

Purpose: search the first-hand research archive of the RCB industry WeChat official account - conference coverage, process cases, application boundaries and institution-level market forecasts. Guidelines: keyword matches title/topic/author/scope; filter with category for a single theme; every item is A-grade (first-hand research) and carries publish date, topic, source URL and AI-readable summary. Limits: Chinese-language source material; A-grade here means first-hand, not independently peer-reviewed; coverage is 63 articles from 2026-04 onward, not the account's full history. Ex: query_articles(keyword='Pyrum'), query_articles(category='市场预测·机构观点'), query_articles(keyword='EPDM', language='en').

Input Schema

Name	Required	Description	Default
`limit`	No	返回条数上限（默认 20，最大 100）
`offset`	No	起始偏移，默认 0；返回体 has_more=true 时用 next_cursor 作为下一页 offset
`keyword`	No	关键词模糊匹配（标题/主题/作者/适用范围），如 '曼谷'、'Pyrum'、'EPDM'、'预测'
`category`	No	主题分类过滤，如 '国际会议·行业动态'、'工艺路线·企业案例'、'市场预测·机构观点'
`language`	No	输出语言	zh
`confidence`	No	置信度过滤（A=公众号一手）
`response_format`	No	输出格式：markdown=人类阅读, json=Agent 处理友好	markdown

Output Schema

Name	Required	Description	Default
`text`	Yes	Human-readable result (markdown, or a JSON string when response_format=json).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

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"
+}

Changed1 schema field changedSep 20, 2026

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"
+}

AddedSep 16, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare this as a safe, idempotent, closed read. The description adds genuinely useful disclosure beyond them: the corpus is Chinese-language source material, coverage is only 63 articles from 2026-04 onward (not the account's full history), and 'A-grade' is clarified as first-hand rather than peer-reviewed. It does not discuss pagination mechanics directly, keeping it just 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.

Conciseness4/5

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

The Purpose/Guidelines/Limits/Ex labeling front-loads the key facts and makes scanning easy. It is somewhat long, but each section carries distinct information, so almost every sentence earns its place.

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?

With an output schema present and 100% schema description coverage, the description need not explain return values, yet it usefully summarizes the item payload (publish date, topic, source URL, AI summary). For a 7-parameter search tool, nothing an agent needs 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 the baseline is 3. The description still adds value: it explains which fields keyword matches, clarifies that category is for a single theme, and supplies three concrete invocation examples including a category and language value that exceed the schema.

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 (search) and resource (the RCB industry WeChat account's first-hand research archive), then enumerates the content scope: conference coverage, process cases, application boundaries, market forecasts. This clearly differentiates it from the sibling get_article, which retrieves a single item.

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

Usage Guidelines4/5

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

Gives actionable usage rules: keyword matches title/topic/author/scope, and category filters to a single theme. It does not explicitly route the agent away from get_article or state when-not-to-use, so it falls short of a 5, but the search/filter context is clear.

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 tools Inspect

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

Need Help?