Skip to main content
Glama

Ashares Sw Industry History

ashares_sw_industry_history
Read-onlyIdempotent

Daily HISTORY of Shenwan (申万) industry indices: dated open, high, low, close, change %, trading amount for one industry code, a list of codes, or all 31 level-1 industries (level=1), trimmed to a window. Answers "申万一级行业近120个交易日收盘", "Shenwan industry index closing prices over 60 days", "which Shenwan industries turned strong over 20/60/120 days", "801010 农林牧渔 historical close", "SW index relative strength". Each industry also gets window_return_pct (first to last close, computed). Window: limit most recent trading days (default 60) or start_date/end_date. Multi-industry calls fetch each series separately (slow: allow ~30 s for level=1); any series that fails is listed under failed, never dropped silently. For ONE day across all industries with P/E and P/B use ashares_sw_industries. Source: Shenwan Hongyuan Research, SW industry index publication.

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": {
      "code": "801010",
      "limit": 120
    },
    "name": "ashares_sw_industry_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoOne 6-digit Shenwan industry code, e.g. "801010" (Agriculture), "801080" (Electronics).
codesNoList of 6-digit Shenwan codes (max 31).
levelNoPass 1 to fetch all 31 level-1 industries in one call (names from the latest board).
limitNoMost recent N trading days within the window, 1-2000 (default 60 when no start_date).
end_dateNoWindow end, YYYY-MM-DD or YYYYMMDD (default: latest).
start_dateNoWindow start, YYYY-MM-DD or YYYYMMDD.

Output Schema

NameRequiredDescriptionDefault
codesNoRequested codes (found:false)
foundNo
failedNoSeries that failed to load
sourceNoPublisher and dataset
windowNo
messageNoPlain-language explanation (found:false)
not_foundNoCodes with no published series
data_as_ofNoLatest bar date
industriesNoOne entry per industry
field_notesNo
industries_returnedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnly/idempotent/openWorld, non-destructive), the description discloses the operational cost of multi-industry calls (~30 s for level=1) and the partial-failure contract: any failed series appears under `failed` rather than being silently dropped. It also reveals a derived field, window_return_pct, computed first-to-last close, which is behavior an agent cannot infer from the schema.

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?

Purpose and scope are front-loaded, then mechanics, then the sibling hand-off — a sensible ordering with no filler sentences. The quoted example-query list is dense and slightly redundant with the trigger phrases already implied, but each sentence still carries operational content.

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?

For a 6-parameter, zero-required read tool with full annotations and an output schema, nothing essential is missing: window semantics, level behavior, latency expectations, failure reporting, and the computed return field are all covered. Return-value structure is legitimately left to the output schema.

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 value by tying parameters together — window selection via `limit` (default 60) versus start_date/end_date, and level=1 meaning all 31 level-1 industries. It does not spell out precedence when limit and a date range are both supplied, which is the main remaining ambiguity.

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?

"Daily HISTORY of Shenwan (申万) industry indices" gives a specific verb-equivalent (retrieve historical daily bars) and resource (SW industry index series), then enumerates the exact fields returned (open/high/low/close/change %/amount). It explicitly names the sibling it is not (ashares_sw_industries for a single day with P/E and P/B), so an agent can route without opening either 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?

Concrete trigger phrasings are supplied ("申万一级行业近120个交易日收盘", "SW index relative strength", "801010 农林牧渔 historical close"), which map real user intents onto this tool. The exclusion is equally explicit: for ONE day across all industries with P/E and P/B, use ashares_sw_industries instead.

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.