Skip to main content
Glama

China Social Financing

china_social_financing
Read-onlyIdempotent

China's total social financing (社会融资规模, TSF): outstanding stock, stock year-on-year growth, and monthly increments by component (RMB loans, foreign-currency loans, entrusted loans, trust loans, bankers acceptances, corporate bonds, government bonds, equity), from the PBOC monthly financial statistics report. month (YYYY-MM) picks the end month, months (1-12) returns that many consecutive months, newest first. Answers "TSF stock growth latest month", "social financing stock year-on-year 2026-09", "new RMB loans and government bond financing in September". Monthly increments are derived from consecutive year-to-date figures and labelled as such. Keyless, sourced live from the People's Bank of China.

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": {
      "month": "2026-09",
      "months": 3
    },
    "name": "china_social_financing"
  }
}

Input Schema

NameRequiredDescriptionDefault
monthNoEnd month as YYYY-MM (e.g. "2026-09"). Omit for the latest published month.
monthsNoHow many consecutive months to return ending at `month`, 1-12 (default 1).

Output Schema

NameRequiredDescriptionDefault
hintNo
foundNo
unitsNo
reasonNo
seriesNo
sourceNo
messageNo
returnedNo
indicatorNo
componentsNo
data_as_ofNo
requested_monthNo
latest_published_monthNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely useful context beyond that: it is keyless, live from the PBOC, and monthly increments are derived from consecutive year-to-date figures and labeled as such — an important caveat about data provenance that the annotations cannot convey. It stops short of the top band because it says nothing about history depth, revision behavior, or latency.

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-loads the resource and the returned measures, then parameters, then example questions, then provenance. Dense but largely waste-free; the component parenthetical and repeated parameter restatement are the only minor redundancy against a 100%-covered schema.

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?

An output schema exists, so return format need not be explained, and the description covers source, derivation of increments, and parameter behavior. The one gap is history coverage — how far back TSF data goes — which matters for a monthly time-series tool but is not stated.

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 coverage is 100%, so `month` (YYYY-MM, omit for latest) and `months` (1-12, default 1) are already fully documented. The description adds one piece of meaning not in the schema — that results come back newest first — but otherwise restates the schema's own semantics.

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?

Names the specific resource (China total social financing, TSF, 社会融资规模), the three measures returned (outstanding stock, YoY growth, monthly increments by component), and the upstream source (PBOC monthly financial statistics). The component list and the domain make it clearly separable from rate/fixing siblings like china_lpr and china_rmb_fixing.

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 concrete usage context by quoting the exact questions it answers (latest stock growth, YoY for a specific month, new RMB loans plus government bond financing). It does not name a sibling tool to defer to or state exclusions, so it falls short of the top band.

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.