Skip to main content
Glama
funinii

TrendRadar

by funinii

search_related_news_history

Find historically related news articles based on a reference text, using customizable time ranges and relevance thresholds to identify connections in past coverage.

Instructions

基于种子新闻,在历史数据中搜索相关新闻

Args: reference_text: 参考新闻标题(完整或部分) time_preset: 时间范围预设值,可选: - "yesterday": 昨天 - "last_week": 上周 (7天) - "last_month": 上个月 (30天) - "custom": 自定义日期范围(需要提供 start_date 和 end_date) threshold: 相关性阈值,0-1之间,默认0.4 注意:综合相似度计算(70%关键词重合 + 30%文本相似度) 阈值越高匹配越严格,返回结果越少 limit: 返回条数限制,默认50,最大100 注意:实际返回数量取决于相关性匹配结果,可能少于请求值 include_url: 是否包含URL链接,默认False(节省token)

Returns: JSON格式的相关新闻列表,包含相关性分数和时间分布

重要:数据展示策略

  • 本工具返回完整的相关新闻列表

  • 默认展示方式:展示全部返回的新闻(包括相关性分数)

  • 仅在用户明确要求"总结"或"挑重点"时才进行筛选

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reference_textYes
time_presetNoyesterday
thresholdNo
limitNo
include_urlNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The MCP tool handler function 'search_related_news_history' in mcp_server/server.py, which acts as the entry point and interface for the tool, calling the underlying search implementation.
    async def search_related_news_history(
        reference_text: str,
        time_preset: str = "yesterday",
        threshold: float = 0.4,
        limit: int = 50,
        include_url: bool = False
    ) -> str:
        """
        基于种子新闻,在历史数据中搜索相关新闻
    
        Args:
            reference_text: 参考新闻标题(完整或部分)
            time_preset: 时间范围预设值,可选:
                - "yesterday": 昨天
                - "last_week": 上周 (7天)
                - "last_month": 上个月 (30天)
                - "custom": 自定义日期范围(需要提供 start_date 和 end_date)
            threshold: 相关性阈值,0-1之间,默认0.4
                       注意:综合相似度计算(70%关键词重合 + 30%文本相似度)
                       阈值越高匹配越严格,返回结果越少
            limit: 返回条数限制,默认50,最大100
                   注意:实际返回数量取决于相关性匹配结果,可能少于请求值
            include_url: 是否包含URL链接,默认False(节省token)
    
        Returns:
            JSON格式的相关新闻列表,包含相关性分数和时间分布
    
        **重要:数据展示策略**
        - 本工具返回完整的相关新闻列表
        - **默认展示方式**:展示全部返回的新闻(包括相关性分数)
        - 仅在用户明确要求"总结"或"挑重点"时才进行筛选
        """
        tools = _get_tools()
        result = tools['search'].search_related_news_history(
            reference_text=reference_text,
            time_preset=time_preset,
            threshold=threshold,
            limit=limit,
            include_url=include_url
        )
        return json.dumps(result, ensure_ascii=False, indent=2)
  • The actual implementation logic of 'search_related_news_history' inside the SearchTools class.
    def search_related_news_history(
        self,
        reference_text: str,
        time_preset: str = "yesterday",
        start_date: Optional[datetime] = None,
        end_date: Optional[datetime] = None,
        threshold: float = 0.4,
        limit: int = 50,
        include_url: bool = False
    ) -> Dict:
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by explaining the relevance calculation (70% keyword overlap + 30% text similarity), threshold effects, limit behavior ('实际返回数量取决于相关性匹配结果,可能少于请求值'), and output format (JSON with relevance scores and time distribution). It also includes important data display policies about when to filter results. However, it doesn't mention rate limits, authentication needs, or potential errors.

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 description is appropriately sized and well-structured with clear sections (Args, Returns, important policies). Most sentences earn their place by providing essential information. However, the threshold explanation could be slightly more concise, and the structure mixes parameter details with behavioral information rather than strictly separating them.

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?

Given the tool's complexity (5 parameters, relevance scoring, historical search), no annotations, but with output schema present, the description provides excellent completeness. It covers purpose, all parameters in detail, behavioral traits, output format, and display policies. The output schema handles return structure, so the description appropriately focuses on semantic context rather than repeating schema details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given 0% schema description coverage, the description must fully compensate, which it does excellently. It provides detailed explanations for all 5 parameters: reference_text purpose, time_preset options with translations, threshold range and calculation details, limit defaults and constraints, and include_url token-saving rationale. This adds substantial meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '基于种子新闻,在历史数据中搜索相关新闻' (search for related news in historical data based on seed news). It specifies the verb '搜索' (search) and resource '相关新闻' (related news) in '历史数据' (historical data). However, it doesn't explicitly differentiate from sibling tools like 'search_news' or 'find_similar_news', which likely have overlapping functionality.

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

Usage Guidelines3/5

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

The description provides some implied usage context: it's for searching historical data based on a reference text, with time presets and relevance thresholds. However, it doesn't explicitly state when to use this tool versus alternatives like 'search_news' or 'find_similar_news', nor does it mention prerequisites or exclusions. The '重要:数据展示策略' section offers output behavior guidance but not usage selection guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/funinii/TrendRadar'

If you have feedback or need assistance with the MCP directory API, please join our Discord server