Skip to main content
Glama

HOLD! Korea Stock Ownership & Insider Trades

get_recent_changes

Read-only

Feed of stake-change filings posted in the last N days (default 7), newest first. Use it across stocks for 'who bought and sold this week', or with entity_id and a large days (up to 730, the stored 2 years) for one holder's filings across all stocks. Insider reports below 1% are left out. ticker limits to one stock; holder or entity_id limits to one holder. For one stock's full history with no date limit, use get_holder_history. Default 50 rows, adjustable with limit. Rows with change listing or non_trade true are not market trades and must be excluded from buy/sell totals. kind is how a 5% filing's new or increased stake arose: buy, placement (rights issue or convertible bond), control (takeover), non_trade, unknown. 최근 N일(기본 7일) 동안 올라온 지분 변동 공시 피드(최신순). 여러 종목을 가로질러 '이번 주 누가 사고팔았나'를 볼 때 쓰고, entity_id와 큰 days(최대 730, 저장된 2년)를 주면 한 보유자의 전 종목 공시 이력이 된다. 1% 미만 임원 보고는 빠진다. ticker를 주면 그 종목만, holder·entity_id를 주면 그 보유자만 거른다. 기간 제한 없이 한 종목의 전체 이력이 필요하면 get_holder_history를 쓴다. 기본 50건이며 limit으로 조절. change가 listing이거나 non_trade가 true인 행은 시장 매수·매도가 아니므로 매매 합계에서 빼야 한다. kind는 5% 공시의 신규·증가 방식이다: buy(매수), placement(증자·전환사채), control(경영권 인수), non_trade, unknown.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_recent_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoLook-back window in calendar days, counted by filing date (as_of). Default 7, up to 730. 공시일 기준 조회 기간(일). 기본 7, 최대 730
limitNoMaximum rows, default 50. Raise it if the feed looks cut off at exactly limit rows. 최대 행 수, 기본 50. 딱 limit건이면 잘린 것이니 올린다
holderNoPart of the filer's name. May mix namesakes; prefer entity_id. 보고자명 일부. 동명이인이 섞일 수 있어 entity_id가 낫다
tickerNoTicker code or exact Korean company name; limits to that stock. Combines with holder/entity_id. 종목코드 또는 정확한 종목명. 주면 그 종목만, holder·entity_id와 함께 쓸 수 있다
entity_idNoentity_id from search_holder. search_holder의 entity_id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / days / description
      Previous value: -"기본 7"New value: +"Look-back window in calendar days, counted by filing date (as_of). Default 7, up to 730. 공시일 기준 조회 기간(일). 기본 7, 최대 730"
    • changedInput schema / properties / entity_id / description
      Previous value: -"search_holder의 entity_id"New value: +"entity_id from search_holder. search_holder의 entity_id"
    • addedInput schema / properties / holder / description
      Added value: +"Part of the filer's name. May mix namesakes; prefer entity_id. 보고자명 일부. 동명이인이 섞일 수 있어 entity_id가 낫다"
    • changedInput schema / properties / limit / description
      Previous value: -"기본 50"New value: +"Maximum rows, default 50. Raise it if the feed looks cut off at exactly limit rows. 최대 행 수, 기본 50. 딱 limit건이면 잘린 것이니 올린다"
    • changedInput schema / properties / ticker / description
      Previous value: -"종목코드 또는 정확한 종목명. 주면 그 종목만"New value: +"Ticker code or exact Korean company name; limits to that stock. Combines with holder/entity_id. 종목코드 또는 정확한 종목명. 주면 그 종목만, holder·entity_id와 함께 쓸 수 있다"
  2. Changed2 schema fields changed
    • addedInput schema / properties / days / description
      Added value: +"기본 7"
    • addedInput schema / properties / ticker
      Added value: +{
      +  "description": "종목코드 또는 정확한 종목명. 주면 그 종목만",
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds substantial context beyond that, including the exclusion of insider reports below 1% and the warning that rows with change=listing or non_trade=true are not market trades and must be excluded from buy/sell totals. It also documents the semantics of the kind field (buy, placement, control, non_trade, unknown) even though no output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The English portion is front-loaded and well ordered: scope, then use cases, then filters, then exclusions and field semantics. However, the entire description is duplicated verbatim in Korean, roughly doubling length with no added information for an English-reading agent.

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?

With no output schema, the description does real work by explaining the row-level fields (change, non_trade, kind) that an agent needs to interpret results correctly. It is only slightly short of full completeness, omitting return shape details such as column ordering or how as_of relates to the days window.

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 each parameter (days, limit, holder, ticker, entity_id) is already documented in the schema, including the 730-day cap and the 50-row default. The description restates the filtering behavior of ticker and holder/entity_id but adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

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 resource and scope: a feed of stake-change filings from the last N days, newest first, with a default of 7 days. It explicitly contrasts itself with the sibling get_holder_history, so an agent can distinguish them without opening either schema.

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?

Gives concrete when-to-use recipes: cross-stock scanning for 'who bought and sold this week', or entity_id plus a large days window for one holder across all stocks. It also names the alternative (get_holder_history) for the no-date-limit, single-stock case and states that ticker narrows to one stock while holder/entity_id narrows to one holder.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources