Skip to main content
Glama
Sign In

China Stocks

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Ashares Turnover Ranking

ashares_turnover_ranking
Read-onlyIdempotent

Market-wide ranking of Chinese A-share stocks by turnover / 成交额排名, 成交额前30名, 成交量排名, or 涨跌幅排名 — the whole board (not specific codes), sorted server-side and returned as a ranked list. Answers 'A股成交额前30名', 'top 30 A-shares by turnover today', 'A股成交量排名', 'A-share market-wide ranking by amount/volume/change %', 'which A-shares traded the most today'. Each row has code, name, price, change %, volume (shares), turnover in CNY (成交额), turnover rate %, and industry (行业/板块, when resolvable). Omit date (or pass today) for the LIVE board (Sina, real-time). Pass a PAST trading day in date for that day's ranking instead of today's — this uses a different, Eastmoney-sourced historical path and only supports sort:'changepercent' (涨跌幅排名): no keyless bulk source for a PAST day's turnover amount or volume ranking was found (Sina's live board is the only amount/volume source), so date + sort:'amount'|'volume' throws a clear error naming that gap rather than silently substituting today's board. A non-trading date (weekend/holiday) walks back to the prior trading day automatically.

Input Schema

NameRequiredDescriptionDefault
dateNoA PAST trading day, YYYY-MM-DD or YYYYMMDD, for that day's ranking instead of today's live board. Only `sort:'changepercent'` is supported with a past date. Omit for the live board.
sortNoRank by turnover amount (成交额, default), change % (涨跌幅), or share volume (成交量). For a PAST `date`, only 'changepercent' is available — 'amount'/'volume' throw a clear error for historical dates (no keyless historical source for those two).
boardNoWhich board to rank: hs_a = all Shanghai+Shenzhen A-shares (default, 沪深A股), sh_a = Shanghai only (沪市A股), sz_a = Shenzhen only (深市A股), cyb = ChiNext (创业板).
limitNoHow many stocks to return, 1–100 (default 30).
orderNodesc (default, highest first) or asc.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "board": "hs_a",
-    "limit": 30,
-    "order": "desc",
-    "sort": "amount"
-  },
-  {
-    "limit": 10,
-    "sort": "changepercent"
-  }
-]New value: +[
+  {
+    "board": "hs_a",
+    "limit": 30,
+    "order": "desc",
+    "sort": "amount"
+  },
+  {
+    "limit": 10,
+    "sort": "changepercent"
+  },
+  {
+    "date": "2026-09-22",
+    "limit": 10,
+    "sort": "changepercent"
+  }
+]
    • addedInput schema / properties / date
      Added value: +{
+  "description": "A PAST trading day, YYYY-MM-DD or YYYYMMDD, for that day's ranking instead of today's live board. Only `sort:'changepercent'` is supported with a past date. Omit for the live board.",
+  "type": "string"
+}
    • changedInput schema / properties / sort / description
      Previous value: -"Rank by turnover amount (成交额, default), change % (涨跌幅), or share volume (成交量)."New value: +"Rank by turnover amount (成交额, default), change % (涨跌幅), or share volume (成交量). For a PAST `date`, only 'changepercent' is available — 'amount'/'volume' throw a clear error for historical dates (no keyless historical source for those two)."
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds real behavior: two different upstream sources (Sina live vs Eastmoney historical), an explicit fail-fast error instead of silently substituting today's board, and automatic walk-back for weekends/holidays. That is substantive context an agent cannot get from the annotations.

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 purpose, then the live-vs-historical constraint, then row shape. It is long and repeats the past-date restriction more than once, but each part is informative rather than padding.

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?

With no output schema, the description supplies the return shape (code, name, price, change %, volume, turnover, turnover rate, industry) and covers the live/historical split, the enum semantics, defaults, and the error path. Nothing material is missing for correct invocation.

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% and every parameter is already documented inline, including the past-date/sort restriction and the board enum meanings. The description largely restates that same material rather than adding new syntax or interaction detail, 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 verb+resource ('market-wide ranking of Chinese A-share stocks by turnover') and explicitly scopes it as 'the whole board (not specific codes)', which separates it from the quote/snapshot style siblings. It also enumerates the returned row fields, so an agent knows exactly what it gets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use rules: omit `date` for the live Sina board, pass a past trading day for the Eastmoney historical path with `sort:'changepercent'` only. It does not name any sibling tool (e.g. ashares_quote, ashares_market_snapshot, ashares_daily_history) as an alternative, so routing still requires inference.

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

All China Stocks toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources