Skip to main content
Glama
Johnhyeon

TelegramLens

by Johnhyeon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

telegram_trending

Read-onlyIdempotent

Find top mentioned stocks and ETFs on Telegram within a chosen period, filter by market (KR/US) and kind, sort by absolute buzz or baseline ratio to spot newly trending tickers.

Instructions

기간 내 텔레그램 언급량 상위 종목을 반환합니다.

종목코드 매칭 전용 — 거시·지정학·테마(예: "미국 이란", "금리") 질문은 telegram_search 사용.

Args: hours: 집계 시간 범위(시간). 기본 24. top: 상위 N개. 기본 20. kind: 종목 종류 — "stock"(개별주만)/"etf"(ETF만)/"all"(전체). 기본 all. market: 시장 — "KR"(국내만)/"US"(미국만)/"all"(전체). 기본 all. kind 와 조합해 국내주식·미국주식·국내ETF·미국ETF 네 갈래로 나뉩니다. 둘 다 all 이면 네 세그먼트를 각각 top 개씩 뽑아 이어 돌려줍니다 (한 랭킹에 섞으면 언급이 많은 국내주식이 정원을 다 먹습니다). 결과의 segments 에 세그먼트별 코드 배열이, 종목마다 market·segment 가 붙습니다. sort_by: 정렬 기준. "buzz_score"(기본, 절대 버즈 크기) / "baseline_ratio"(평소 대비 배율). ⚠️ buzz_score 는 절대 언급량이라 삼성전자·SK하이닉스 같은 대형주가 거의 항상 상위에 옵니다. 이 종목들은 평소에도 많이 언급되므로 "지금 새로 뜨는 곳"과는 다릅니다. 새로 관심이 붙는 종목을 찾으려면 sort_by="baseline_ratio" 를 쓰세요 — 그 종목의 평소 언급량 대비 몇 배인지로 줄을 세웁니다(3배 이상이면 새 이야기가 붙는 중). min_independent: baseline_ratio 정렬에서 요구할 최소 독립 언급 수. 0이면 기본값 3이 적용됩니다. 배율은 평소 언급이 적을수록 커지므로 (7일에 1건 → 오늘 1건 = 7배), 이 바닥이 없으면 한두 건짜리 종목이 상위를 채웁니다. buzz_score 정렬에는 영향을 주지 않습니다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNo
kindNo
hoursNo
marketNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.7.0
    • removedInput schema / properties / hours / default
      Removed value: -24
    • removedInput schema / properties / kind / default
      Removed value: -"all"
    • removedInput schema / properties / market / default
      Removed value: -"all"
    • removedInput schema / properties / top / default
      Removed value: -20
  2. Changed1 schema field changedv0.6.1
    • addedInput schema / properties / market
      Added value: +{
+  "default": "all",
+  "title": "Market",
+  "type": "string"
+}
  3. First observedv0.4.3

TDQS

A5/5.0
Behavior5/5

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

The description reveals non-obvious behaviors beyond what annotations provide: the four-way segment split when kind and market are both 'all', the result structure containing `segments`, `market`, and `segment`, and the buzz_score bias toward large caps like Samsung Electronics and SK Hynix. It also exposes the min_independent default of 3 and why it exists to prevent one-off mentions from dominating baseline_ratio ranking. These behavioral details are crucial for correct invocation.

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 purpose is front-loaded in the first sentence, followed immediately by a routing rule to a sibling. The Args section is a clean bulleted list with defaults, allowed values, and inline warnings that add context without redundant text. Every paragraph serves a distinct purpose: behavior explanation, ranking-pitfall warning, or parameter semantics.

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 covers purpose, usage boundary, parameter semantics, default behaviors, output structure, and a sibling alternative. It also warns about ranking pitfalls so the agent can choose the correct sort_by. With read-only annotations and an output schema present, nothing essential for correct invocation is left undocumented.

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?

The schema has 0% description coverage)Skip over the schema. The description documents all schema-listed parameters (hours, top, kind, market) with defaults, allowed values, combinations, and interactions, and even documents sort_by and min_independent, which are absent from the schema. This far exceeds compensation for the schema's silence.

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 the exact function: '기간 내 텔레그램 언급량 상위 종목을 반환합니다' (returns top stocks by Telegram mention volume within a period), with a clear verb and resource. It also explicitly differentiates itself by saying '종목코드 매칭 전용' and pointing non-stock queries to telegram_search. This fully distinguishes it from siblings.

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?

It explicitly says this tool is for stock code matching only, and tells the agent to use telegram_search for macro/geopolitical/theme questions. It also provides decision guidance inside the tool via sort_by, recommending baseline_ratio when the agent's intent is to find '새로 관심이 붙는 종목' (newly gaining attention). This is explicit when/when-not guidance with a named alternative.

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