Skip to main content
Glama

Mofcom Odi

mofcom_odi
Read-onlyIdempotent

China's non-financial outward direct investment (对外直接投资, ODI) — monthly YEAR-TO-DATE CUMULATIVE amount in USD 100M, number of enterprises investing abroad, and the count of countries/regions reached, each with year-over-year %. Sourced live from MOFCOM's (商务部) data centre, keyless. Values reset down every January (累计 = Jan-through-month, not a standalone monthly flow) — the response's note field restates this. No per-country breakdown is available (the country count is a COUNT, not a split by destination). Answers "China's outward FDI this year", "how many Chinese enterprises are investing abroad", "China ODI growth rate".

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": {
      "end_period": "2026-09",
      "start_period": "2026-01"
    },
    "name": "mofcom_odi"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows to return, newest first (default 24, max 500). Ignored range still comes from start_period/end_period — this only caps how many of those rows come back.
end_periodNoLatest period to include, as YYYYMM or YYYY-MM. Omit for the most recent available month.
start_periodNoEarliest period to include, as YYYYMM or YYYY-MM (e.g. "2024-01" or "202401"). Omit for full history.

Output Schema

NameRequiredDescriptionDefault
noteNo
rowsNo
foundNo
sourceNo
returnedNo
data_as_ofNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the description is free to spend its words on non-obvious behavior — and it does: values are YTD cumulative and reset every January, the response carries a `note` field restating this, and the source is live and keyless. The YTD reset caveat is exactly the kind of trap an agent would otherwise misread as a monthly flow.

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 metrics, then caveats, then trigger questions — a sensible ordering with no filler sentences. It is dense (heavy em-dash and parenthetical use) and slightly longer than needed, but every clause carries substantive 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 detail is not required; the description instead covers what an agent cannot infer — YTD semantics, the January reset, the absence of destination breakdown, and keyless live sourcing. For a three-optional-parameter read tool, nothing material is missing.

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 description coverage is 100%, and the schema already explains the YYYYMM/YYYY-MM formats, defaults, and how `limit` interacts with the period range. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 a specific resource (China's non-financial outward direct investment), the exact metrics returned (YTD USD 100M amount, enterprise count, country/region count, each with YoY %), and the source (MOFCOM data centre). The parenthetical '对外直接投资' and the contrast with 'the country count is a COUNT, not a split by destination' distinguishes it from inbound-FDI siblings like mofcom_fdi_utilised.

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 trigger questions ('China's outward FDI this year', 'how many Chinese enterprises are investing abroad', 'China ODI growth rate') and an explicit exclusion (no per-country breakdown available), which prevents a mis-call for destination-level data. It stops short of naming sibling tools to route to for related MOFCOM datasets, so it is clear context without full alternative routing.

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.