Skip to main content
Glama

Ashares Intraday Bars

ashares_intraday_bars
Read-onlyIdempotent

Intraday minute bars (分钟线/分时/分钟K线) for Chinese A-share stocks/ETFs on a given trading日/交易日, with cumulative volume and turnover (累计成交量/累计成交额) computed up to a requested time of day (截至, e.g. 截至11:05), answers '515050在2026-09-01这个交易日截至11:05的累计成交量和累计成交额', '600519某个交易日截至某时刻的累计成交量和成交额', 'cumulative volume for 600519 up to 11:05 on a past trading day', 'intraday minute bars for an A-share on a specific date'. ashares_quote is realtime-only (today, right now) and ashares_daily_history is end-of-day-only (no intraday granularity), this tool is for a PAST trading日's intraday trajectory. Returns the interval bars for that day plus cumulative_volume_shares/cumulative_turnover_cny summed from the day's open through up_to (or the whole day if up_to is omitted). symbols takes a bare 6-digit code (e.g. "515050") or the sh/sz/bj-prefixed form, same as ashares_quote. Bounded lookback: the upstream caps total bars at ~1950 regardless of interval, so retention shrinks as the interval shrinks, roughly 8 trading days at 1-minute, 40 at 5-minute (the default), 110 at 15-minute, a year at 30-minute, two years at 60-minute, and it slides forward daily. A date older than a result's earliest_bar_date_available is out of range for that interval; try a coarser interval, or use ashares_daily_history for daily (not intraday) history further back. Source: Sina (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": {
      "date": "2026-09-01",
      "up_to": "11:05",
      "symbols": "515050,600519"
    },
    "name": "ashares_intraday_bars"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesThe trading day the bars are for, YYYY-MM-DD or YYYYMMDD, e.g. "2026-09-01".
up_toNoTime of day (24-hour, Beijing time) to cumulate volume/turnover through, e.g. "11:05". Omit for the whole trading day (or "as of now" if `date` is today and the market is open).
symbolsYesOne 6-digit code or a comma-separated list, up to 5, e.g. "515050" or "600519,000001". sh/sz/bj prefixes accepted but optional. ETF codes work the same as stock codes.
intervalNoBar interval in minutes. Default "5". Smaller intervals keep a shorter lookback window, see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / interval / description
      Previous value: -"Bar interval in minutes. Default \"5\". Smaller intervals keep a shorter lookback window — see the tool description."New value: +"Bar interval in minutes. Default \"5\". Smaller intervals keep a shorter lookback window, see the tool description."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget on non-structured behavior: the ~1950-bar upstream cap and its per-interval retention consequences (~8 days at 1-minute through two years at 60-minute, sliding forward daily), plus the Sina keyless source. It also explains what the cumulative fields sum over (open through `up_to`, or the whole day when omitted).

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 alternatives, then retention, then parameter notes and source — a sensible information hierarchy. The main inefficiency is four near-identical example phrasings of the same cumulative-volume question, two in Chinese and two in English, which could be collapsed to one or two.

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 carries the return-value burden and does so by naming the returned interval bars and the cumulative_volume_shares/cumulative_turnover_cny fields, plus the earliest_bar_date_available signal. The only shortfall is that response shape beyond those field names (ordering, per-symbol grouping on multi-symbol requests) is left implicit.

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 still adds real meaning by tying `interval` to the retention table and clarifying that `symbols` accepts bare or sh/sz/bj-prefixed codes 'same as ashares_quote', and that omitting `up_to` means whole-day (or as-of-now for today). It does not restate every schema detail, but the added semantics are genuine rather than duplicative.

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 opens with a specific resource (intraday minute bars for Chinese A-share stocks/ETFs) plus the distinguishing computation (cumulative volume/turnover up to a requested time of day), with Chinese synonyms (分钟线/分时/分钟K线) to anchor retrieval. It explicitly separates itself from the two nearest siblings: ashares_quote is realtime-only and ashares_daily_history is end-of-day-only.

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 the exact selection condition (a PAST trading day's intraday trajectory) against named alternatives, and goes further by handling the fallback case: if `date` precedes `earliest_bar_date_available`, try a coarser interval or fall back to ashares_daily_history. Sample questions make the intended query shape unambiguous.

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.