Trustbase Lab · Trusted Data Infrastructure for the AI Era

Search Knowledge Cards

query_cards

Read-onlyIdempotent

Purpose: search the public knowledge-card collection - atomic sourced facts compiled from statistics, standards, papers and official announcements. Guidelines: keyword matches title and fact fields; combine type and region to narrow; every card returns its fact summary together with the source it was compiled from. Limits: publicly releasable cards only - gated or internal cards are never returned; each card is a single fact rather than analysis, and carries no recommendation. Ex: query_cards(keyword='ISCC'), query_cards(type='标准解读', region='欧盟').

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	可选：卡片类型
`limit`	No	返回条数上限（默认 20）
`region`	No	可选：区域关键词
`keyword`	No	关键词（标题与事实字段全文匹配）

Output Schema

TableJSON 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 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 17, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the read-only/idempotent annotations, the description discloses useful behavior: only publicly releasable cards are ever returned, each result includes a fact summary with its source, and cards contain a single fact rather than analysis or recommendations. No statement contradicts the annotations.

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?

The description is compact and well-structured with labeled sections: Purpose, Guidelines, Limits, and Ex. It front-loads the core purpose, and every sentence carries useful information without padding.

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?

The description fully covers scope, matching behavior, result contents, exclusions, and usage examples. An output schema exists, so detailed return-value documentation isn't required here; nothing essential is missing for an agent to invoke query_cards correctly.

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 description coverage is 100%, so all four parameters are already documented. The description adds usage nuance (combine type and region to narrow, keyword matches title and fact fields) and examples, but those largely restate schema meaning rather than adding new parameter 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?

The description opens with a clear verb ('search') and resource ('public knowledge-card collection'), then defines the collection as atomic sourced facts compiled from statistics, standards, papers, and official announcements. This makes the tool's scope immediately distinguishable from sibling query tools for articles, companies, policies, and trade flows.

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?

A dedicated 'Guidelines' section explains how keyword matching works and advises combining type and region to narrow results, followed by concrete examples. It doesn't explicitly state when to prefer this over siblings, but the context is clear enough that an agent can apply it correctly.

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?