Skip to main content
Glama

Cn Index Constituents

cn_index_constituents
Read-onlyIdempotent

CONSTITUENTS and WEIGHTS of a China Securities Index Co. (CSI) or SSE index by code: every constituent stock with its weight (%), exchange and the file date, the weight total, plus the index's sector weights (CSI level-1 sectors such as Financials 22.6%, Information Technology 19.3%, and level-2 industry groups such as Banks) and its top-10 holdings with their sector. Answers "CSI 300 constituents and weights", "沪深300 成分股 权重", "CSI 300 sector weights", "沪深300 行业权重", "what are the biggest holdings of CSI 500 (000905)", "CSI 1000 constituents 000852". Constituent weights come from the index's daily close-weight publication and are dated by constituents_as_of; sector weights and top-10 come from CSI's index page data and carry their own sector_weights_as_of (the two can differ by days). Per-constituent sector is published only for the top 10; for the rest use the stock's own profile. Code is case-sensitive upstream: numeric codes as 6 digits (000300, 000905, 000852, 000016), letter-prefixed ones upper-case (H30269). An unknown or unpublished code returns found:false. Source: China Securities Index Co., index constituent weights and sector weights.

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": {
      "limit": 10,
      "index_code": "000300"
    },
    "name": "cn_index_constituents"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax constituents returned, largest weight first, 1-2000 (default: all). constituent_count and weight_total_pct always cover the whole index.
index_codeYesCSI/SSE index code, e.g. "000300" (CSI 300), "000905" (CSI 500), "000852" (CSI 1000), "000016" (SSE 50), "000922" (CSI Dividend).

Output Schema

NameRequiredDescriptionDefault
foundNo
sourceNo
messageNo
data_as_ofNo
index_codeNo
sector_noteNo
top10_as_ofNo
constituentsNo
index_name_cnNo
sector_weightsNo
top10_holdingsNo
weight_total_pctNo
constituent_countNo
constituents_as_ofNo
sector_weights_as_ofNo
industry_group_weightsNo

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, and the description goes well beyond them: two separate as-of dates that can differ by days, per-constituent sector published only for the top 10, and found:false for unknown or unpublished codes. That provenance and edge-case detail is exactly the kind of context annotations cannot carry. The 4 rather than 5 reflects that the freshness/latency of the underlying publication is implied but never stated outright.

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 the payload, then caveats (dual as-of dates, top-10-only sector, code casing, found:false) in descending order of importance. The quoted example-query run is somewhat repetitive against the schema's own examples and the Chinese strings could be trimmed, but each remaining sentence carries operational information.

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?

An output schema exists, so return-shape explanation is unnecessary, and for a two-parameter read the description still covers provenance, date semantics, partial-field coverage, casing constraints and the not-found path. Nothing an agent needs to invoke this correctly 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?

With 100% schema coverage the baseline is 3, and the description earns the extra point by documenting upstream code formatting rules (six-digit numeric codes, upper-case letter-prefixed codes like H30269) that the schema does not state. The limit parameter's largest-weight-first ordering and full-index coverage of counts/totals are already in the schema, so the description rightly does not belabor them.

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 pair (constituents and weights of a CSI/SSE index by code) and enumerates exactly what comes back: per-stock weights with exchange and file date, weight total, sector weights at both CSI levels, and top-10 holdings with sector. It is clearly distinguishable from a valuation-style sibling by focusing on membership and weight data rather than pricing metrics.

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?

Provides concrete trigger phrasings in English and Chinese ("CSI 300 constituents and weights", "沪深300 成分股 权重", "CSI 300 sector weights", "what are the biggest holdings of CSI 500") plus sample codes, so an agent can pattern-match a request to this tool. It stops short of explicitly naming a sibling tool and saying when not to use this one, so it is clear context rather than full routing guidance.

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.