Skip to main content
Glama

Ashares Sector Capital Flow Window

ashares_sector_capital_flow_window
Read-onlyIdempotent

China A-share INDUSTRY-SECTOR main-capital net inflow summed over the last N trading days (default 5; use 3, 5 or 10), with how many days in a row each sector has had net inflow or outflow. Answers '最近5日行业主力资金净流入排名', '板块连续3日净流入', '连续流入天数', 'which sectors had the most main-capital net inflow over the last 10 trading days', 'sectors with net inflow for 3 days running', 'sector fund flow 5-day ranking'. Per sector: summed main net inflow (主力净流入) and its order-size split (超大单/大单/中单/小单) in CNY, inflow and outflow day counts, the current consecutive inflow or outflow streak, cumulative change %, and the day-by-day net inflow. Rank with sort (summed inflow, streak length, cumulative change, inflow days) and filter one sector with sector (name fragment or board code). Eastmoney industry boards (行业板块), roughly 128 sectors, history from 2021-11; not the Shenwan classification. For a single day use ashares_sector_capital_flow. Source: Eastmoney datacenter (keyless).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "days": 10,
      "limit": 3
    },
    "name": "ashares_sector_capital_flow_window"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoWindow length in trading days, 1-20 (default 5; 3, 5 and 10 are the common asks).
sortNoRank by summed net inflow (default), current consecutive inflow streak, cumulative change %, or number of inflow days.
limitNoHow many sectors to return, 1-130 (default 20).
orderNodesc (default, largest first) or asc (largest net outflow / shortest streak first).
sectorNoOnly sectors whose name contains this text (e.g. "半导体") or whose board code equals it (e.g. "BK1036").
end_dateNoLast day of the window, YYYY-MM-DD or YYYYMMDD (default: most recent day with published data).

Output Schema

NameRequiredDescriptionDefault
noteNoHow the figures are defined
sortNoRanking column used
foundNofalse only when no data was published in range
orderNodesc or asc
sourceNoPublisher and dataset
messageNoWhy nothing was found, when found is false
sectorsNoRanked sectors
end_dateNoLast trading day in the window, YYYY-MM-DD
returnedNoSectors returned
data_as_ofNoSame as end_date
window_noteNoSet when the window is shorter than requested
total_sectorsNoSectors with data in the window before the limit
requested_daysNoWindow length asked for
dates_oldest_firstNoTrading dates in the window, oldest first
window_trading_daysNoTrading days actually covered by the window

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

The annotations already declare readOnly, idempotent, non-destructive and openWorld, so the description's job is to add operational context. It adds that the source is Eastmoney datacenter (keyless), that the coverage is roughly 128 industry boards, that the history starts in 2021-11, and what the default end_date means. It does not cover refresh cadence or data latency, so it stops short of 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?

The purpose is front-loaded in the first clause, and the parameter and field notes follow logically. However, the long run of paraphrased example queries ('板块连续3日净流入', 'sectors with net inflow for 3 days running', 'sector fund flow 5-day ranking') repeats the same intent, and the per-sector field list overlaps the output schema.

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?

Given the six optional parameters and an existing output schema, the description covers everything needed: defaults, ranges, ranking and filter semantics, the data universe, and the single-day alternative. Return-format explanation is unnecessary because the output schema carries it.

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%, with per-parameter text and enums already documenting `days`, `sort`, `order`, `limit`, `sector` and `end_date`, so the baseline is 3. The description reinforces meaning with worked query examples (5-day ranking, 3-day streak, sector fragment or board code), but it adds little syntax or edge-case detail beyond the schema.

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?

A specific verb-and-resource statement: industry-sector main-capital net inflow summed over N trading days, plus per-sector streak counts. It also scopes the data universe (Eastmoney industry boards, ~128 sectors, history from 2021-11, not the Shenwan classification), so an agent can distinguish it from ashares_sector_capital_flow and related flow tools without opening a 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?

It states an explicit alternative and the condition that selects it: 'For a single day use ashares_sector_capital_flow.' It also says the default window is 5 days and that 3, 5 and 10 are the common asks, and it describes how to rank and narrow results, so the agent knows both how to use the tool and when to use another one.

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.