Skip to main content
Glama
trend-radar-mcp

trend-radar-mcp

by ngwddd

radar_potential

潜力新闻(opt-in):用现有扫描 + 历史 run 的「新增独立源」做数值预排,返回 8–12 条候选,交给模型判断谁最可能成为今天的爆点。

Instructions

潜力新闻(opt-in):用现有扫描 + 历史 run 的「新增独立源」做数值预排,返回 8–12 条候选,交给模型判断谁最可能成为今天的爆点。

不传这个工具时 radar_scan 的返回完全不变;默认 5 分钟内直接复用上一次 run,不重复抓取。适合凌晨热度还没起来、按「已传播」排不出东西的时候。

返回 candidates(score/signals/why)与 meta(degraded/caveat)。caveat 固定为「未验证」,不要写成已确认新闻;不要与 core/watch 混排。

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": {
      "query": "<query>"
    },
    "name": "radar_potential"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNo
daysNo回看窗口。凌晨用 1 天即可。
queryYes用户原话,用于判 scope。
domainNoauto
reuse_lastNo5 分钟内有同 scope 的 run 就直接复用,0 网络。
force_refreshNo
lookback_runsNo
max_per_sourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.4

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the no-side-effect nature on radar_scan, the 5-minute reuse/zero-network caching behavior, the returned structure (candidates + meta with degraded/caveat), the fixed 'unverified' caveat, and a mixing warning. It omits permission/auth profile and explicit read-only declaration, keeping it from 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?

It is front-loaded with the what-and-why, then usage guidance, then return shape and caveat rules. Four paragraphs are all substantive and earn their place, though it is on the denser side.

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?

There is no output schema, and the description usefully explains the return (candidates with score/signals/why, meta with degraded/caveat) plus the critical caveat-handling rule. For an 8-param ranking tool with no annotations, it is nearly complete but leaves some parameters and safety profile underspecified.

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 coverage is low (38%), and the description only compensates for a portion: it clarifies reuse_last caching semantics, the top output count range, and the early-morning days intent. It adds no meaning for domain, force_refresh, lookback_runs, or max_per_source, leaving four of eight params undocumented across both schema and description.

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 states a specific resource (potential breaking news) and what the tool produces: a numeric pre-ranking of 8–12 candidate items for the model to judge as today's likely breakout. It explicitly distinguishes itself from the sibling by noting radar_scan's return is unchanged when this tool is not used, so the agent can tell them apart without inspecting schemas.

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?

It gives a concrete when-to-use condition ('适合凌晨热度还没起来、按「已传播」排不出东西的时候') and establishes it as opt-in with 5-minute reuse default. It names the radar_scan relationship but does not explicitly contrast with radar_check/radar_pack or state when not to use it.

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

Deploy Server

Other Tools