Skip to main content
Glama

Ashares Market Overview

ashares_market_overview
Read-onlyIdempotent

A-share market-wide DAILY OVERVIEW by date, per exchange and combined: number of listed stocks, trading amount, total market cap, float (tradable) market cap and turnover rate (换手率), for the Shanghai (SSE) and Shenzhen (SZSE) exchanges, all in 100 million CNY (亿元). Answers "A-share daily turnover rate for 60 trading days", "全市场换手率", "沪深流通市值", "A-share total and float market cap on 2026-11-12", "margin balance as a share of float market cap" (divide ashares_margin_financing by float_market_cap_100m_cny), "两市成交额". Pass date, or start_date + end_date (or days, default 1 = latest trading day) for a history of one row per trading day, newest first. The SSE turnover rate is the exchange's published float-based figure; the SZSE rate and the combined rate are COMPUTED as trading amount / float market cap and labelled so. Covers stocks only (not funds or bonds). If either exchange cannot be read for a day, that day carries the error and no combined figure rather than presenting half the market as the market. Non-trading days are skipped. Source: Shanghai Stock Exchange and Shenzhen Stock Exchange, daily market overview.

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": {
      "date": "2026-11-12"
    },
    "name": "ashares_market_overview"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoOne trading day, YYYY-MM-DD or YYYYMMDD. A non-trading day returns found:false with the nearest prior trading day.
daysNoMost recent N trading days, 1-90 (default 1). Closed days are served from a stored copy (each day says per exchange whether it came from the store or a live read); only days not yet stored cost live exchange calls, so a first long call may stop early with resume_end_date and the next call is faster. Missing days are listed, never silently dropped.
end_dateNoRange end (YYYY-MM-DD).
start_dateNoRange start (YYYY-MM-DD). Use with end_date (default: latest).

Output Schema

NameRequiredDescriptionDefault
dateNox
daysNoOne row per trading day, newest first
foundNo
failedNox
sourceNoPublisher and dataset
messageNox (found:false)
partialNo
end_dateNox
data_as_ofNoLatest trading day
start_dateNox
field_notesNo
partial_noteNox
shortfall_noteNox
resume_end_dateNoPass as end_date to continue
trading_days_returnedNo
trading_days_requestedNo
nearest_prior_trading_dayNox
days_with_unreadable_exchangeNoDays where an exchange could not be read

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / days / description
      Previous value: -"Most recent N trading days, 1-90 (default 1). Each day is two exchange calls, so large N is slow; missing days are listed, never silently dropped."New value: +"Most recent N trading days, 1-90 (default 1). Closed days are served from a stored copy (each day says per exchange whether it came from the store or a live read); only days not yet stored cost live exchange calls, so a first long call may stop early with resume_end_date and the next call is faster. Missing days are listed, never silently dropped."
  2. Added

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint), so the bar is lower, but the description still earns credit by disclosing that the SZSE and combined turnover rates are computed rather than published, and that a failed exchange read suppresses the combined figure instead of presenting half a market. That is exactly the kind of provenance and partial-failure behavior annotations cannot express.

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

Conciseness5/5

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

The lead sentence front-loads what the tool returns and in what unit (亿元), then layers in usage, caveats, and source. It is dense but every clause carries information — the example phrasings, the computed-vs-published note, and the stocks-only scope all affect correct invocation.

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 four optional parameters, an output schema that carries return shape, and full annotation coverage, the description supplies everything an agent needs before calling: units, exchange coverage, date-mode selection, provenance, error semantics, and non-trading-day handling. Nothing material is missing.

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 would be 3, but the description adds real meaning: it frames `date`, `start_date`/`end_date`, and `days` as alternative modes and states the output ordering (one row per trading day, newest first, default 1 = latest trading day). That resolves selection ambiguity the schema leaves implicit.

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?

The description names a specific verb and resource — a daily, market-wide A-share overview across SSE and SZSE — and enumerates exactly what metrics are returned (listed count, turnover amount, total and float market cap, turnover rate). It also distinguishes itself from sibling tools by tying directly to ashares_margin_financing for the margin-share calculation, so an agent can place it without opening the schema.

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?

It gives concrete usage conditions: pass `date` for one day, `start_date`+`end_date` for a range, or `days` (default 1 = latest trading day) for recent history, and it spells out the scope exclusion ('covers stocks only, not funds or bonds'). What it does not do is route the agent away from this tool toward a sibling for narrower queries, but the when-to-use guidance is otherwise explicit.

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.