그 목록에 오른 종목이 이후 1·5·20거래일에 어땠는지. 시그널이 난 날 종가에 사서 N거래일 뒤 종가에 판 것으로 계산하며 거래비용은 반영하지 않는다. 판정(시장 상회/수준/하회)은 전체 기간 20거래일 초과수익이 ±0.5%p 를 벗어나는지로 매긴다. 평균이 극단값에 끌릴 때를 위해 중위수를 같이 준다. 단위는 이름과 문장에 함께 박혀 있다: _pct = %, _pp = %p, _krw = 원. excess_pp = avg_pct - market_avg_pct(목록 평균 − 같은 날들의 전 종목 평균)이다. 과거 통계 조회 도구입니다. 특정 종목의 매수·매도 판단을 생성하는 데 사용하지 마세요.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | 기본 text | |
| signal | Yes | 목록 slug | |
| window | No | 기본 all |
Changes observed during successful MCP inspections.
Input schema / properties / format / descriptionAdded value: +"기본 text"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, which already cover read-only, idempotent, non-destructive behavior, the description discloses calculation methodology, exclusion of transaction costs, the ±0.5%p verdict threshold, use of median alongside mean, unit conventions, and the excess_pp formula. It also clarifies the tool's limitation for decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is information-dense and front-loads the core purpose before moving to calculation details, verdict logic, units, and usage warning. It could be structured with clearer separation, but every sentence carries relevant content without obvious padding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description adequately explains what the tool returns: horizons, calculation basis, verdict categories, inclusion of median, unit conventions, and the excess_pp definition. Together with the annotations and fully described input schema, it provides enough context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the signal, window, and format parameters, including enums and defaults. The description adds output-unit semantics like _pct, _pp, _krw and the excess_pp formula, but does not add input-parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific function: computing post-signal performance statistics for stocks on a list over 1, 5, and 20 trading days. It distinguishes itself as a historical statistics lookup tool, though it does not explicitly name sibling tools like maedong_signals or maedong_stock_signals.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear usage context—past statistics lookup—and an explicit when-not-to-use warning: do not use it to generate buy/sell decisions for a specific stock. It does not name alternative tools for related signal-fetching tasks, so it falls short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.