Skip to main content
Glama

ラジ株ナビ (Radikabunavi) - Japanese stock data from EDINET/TDnet

監視リストを見る

get_watchlist
Read-only

監視リストの一覧を取得します。 監視リストの銘柄は、お気に入り(ポートフォリオ。category: favorite)と監視(category: watching)に分かれます。 お気に入り(ポートフォリオ)は、保有などを自分で管理する銘柄で、株数(shares)と取得単価(acquisitionPrice・円)を任意で持てます。株数を入れれば保有(holding: true)として扱います。メモは付けられません。 「ポートフォリオに入れて」「お気に入りに入れて」という依頼は category: favorite にあたります。 監視は、気になる銘柄です。メモを付けられます。分類を省略すると監視になります。 同じ銘柄をお気に入りと監視の両方に入れられます(その場合は分類ごとに別の項目です)。

各銘柄に category・holding(株数1以上なら true)を返し、お気に入りには shares・acquisitionPrice も返します。 保有銘柄だけを見るには holding: true、お気に入り(ポートフォリオ)だけなら category: favorite、監視だけなら category: watching を指定します。 件数は count(今回返した件数)、totalCount(全体)、favoriteCount、watchingCount で返します。limit は監視の件数上限です。

メモ(note)は監視の銘柄にだけあり、その銘柄で何を気にしているかが書かれています。 登録日(addedAt)はメモを書いた時点で、上書きされません。 lastCheckedAt は前回この一覧を取得した時刻です(この時刻の記録だけは今回の取得で更新します。登録内容・メモは変えません)。 この2つの間に何が起きたかは、get_timely_disclosures / get_large_holdings / get_earnings_forecast などで確認できます。

※この一覧取得は登録銘柄数ぶん利用回数を使います(0件・1件なら1回)。絞り込んでも、全体の登録数で数えます。

※ 本データは情報提供を目的とし、投資助言・推奨ではありません。

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_watchlist"
  }
}

Input Schema

NameRequiredDescriptionDefault
holdingNo保有で絞り込む(任意)。true = 株数1以上のお気に入り、false = それ以外
categoryNo分類で絞り込む(任意)。favorite = お気に入り(ポートフォリオ)、watching = 監視

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / category
      Added value: +{
      +  "description": "分類で絞り込む(任意)。favorite = お気に入り(ポートフォリオ)、watching = 監視",
      +  "enum": [
      +    "favorite",
      +    "watching"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / holding
      Added value: +{
      +  "description": "保有で絞り込む(任意)。true = 株数1以上のお気に入り、false = それ以外",
      +  "type": [
      +    "string",
      +    "boolean"
      +  ]
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/destructiveHint/openWorldHint annotations by disclosing a non-obvious side effect (this call updates lastCheckedAt while leaving notes and registration untouched) and a cost model (credits consumed proportional to the total number of registered stocks, including when filtering, minimum 1). It also states what is NOT possible (notes only exist on watching entries; favorite entries cannot hold notes) and what is returned. Minor note: the disclosed timestamp write means the call is not strictly side-effect free despite readOnlyHint=true, but the description is honest about it rather than contradicting it.

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?

Front-loaded with the purpose and then organized by concept (categories → filtering → return fields → notes/timestamps → cost → disclaimer). Every block carries real information, but the length is driven by return-value detail that has to live somewhere because there is no output schema. Some redundancy exists, e.g. the holding/shares rule is stated twice and the category semantics are revisited in the filtering paragraph.

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 correctly compensates by documenting the returned fields (category, holding, shares, acquisitionPrice, note, addedAt, lastCheckedAt, count/totalCount/favoriteCount/watchingCount) and the credit cost model. What holds it back is the dangling 'limit' reference with no matching parameter and no ordering/pagination statement, leaving the agent to guess how result ordering works.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns extra by explaining the derived relationship behind 'holding' (true means shares ≥ 1 on a favorite entry, so the agent understands holding is computed from shares rather than being an independent flag) and by spelling out the portfolio vs watch semantics of each category value. It references a 'limit' parameter that does not exist in the input schema, which is a small inconsistency that keeps this from a 5.

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?

Opens with a specific verb+resource ('監視リストの一覧を取得します') and immediately splits the resource into its two real sub-collections (favorite vs watching), which is exactly the distinction an agent needs to reason about the sibling tools add_to_watchlist / remove_from_watchlist / update_watchlist_note. The read/list role versus those mutating siblings is unambiguous.

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?

Explicitly maps natural-language user intents to parameters ('「ポートフォリオに入れて」…は category: favorite'), gives the default when the filter is omitted (監視), and states the concrete filter recipes (holding: true, category: favorite, category: watching). It also routes the agent to the right siblings for follow-up questions ('この2つの間に何が起きたかは、get_timely_disclosures / get_large_holdings / get_earnings_forecast などで確認できます').

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