TradeStats - customs trade statistics

get_supplier_dependency

Concentration of the supplying countries behind a named indicator or an HS code over the latest 12 months: the Herfindahl index (hhi, 0 to 1; score_points is the same figure on the 0 to 10,000 scale), the share of the largest supplier and of the top three, the number of supplying countries, how hhi moved against 1 and 3 years earlier (more_diversified, little_change or more_concentrated) and the main suppliers. Give either "indicator" (only indicators with a breakdown by partner country, called "by origin" or "by destination", have one; others answer dependency_not_applicable) or "reporter" and "code" (flow defaults to import; for exports it measures the concentration of destinations; an HS code answers for the latest month only). Use it for questions about how concentrated the sources of a product are and whether they are concentrating or diversifying. The hhi is a mathematical measure of concentration, not a forecast; the partner country is the country of origin or of consignment depending on the reporter and can include transshipment; the 0.02 change used for the direction labels is our convenience threshold, not a standard. For an HS code, top3_share and top_suppliers are shares of the world 12-month total (partners without a country code included in the total), while hhi uses partners with a country code only. Reference information computed mechanically from public statistics; not investment advice, a credit rating or a trading recommendation.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_supplier_dependency"
  }
}

Input Schema

Name	Required	Description
`code`	No	HS product code of 2, 4 or 6 digits or the national code of the reporter; dots are ignored (for example "850760"). Give this (with reporter) or indicator, not both.
`flow`	No	Optional, codes only. "import" (default: the supplying countries) or "export" (the destination countries).
`month`	No	Optional. The month the 12 months end in, YYYY-MM; default the latest month. An HS code answers for the latest month only.
`reporter`	No	The reporting country (JP, US, GB or EU). Required with code; not used with indicator.
`indicator`	No	The indicator id (for example "jp.naphtha.import_by_origin"), an alias in English or Japanese, or a few distinctive words; see list_indicators. Give this or code, not both.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the dependency_not_applicable outcome, that only indicators with a by-origin/by-destination breakdown qualify, that HS-code answers cover the latest month only, and that top3_share and hhi use different denominators. It also flags known data caveats (transshipment, partner country of origin vs consignment, the 0.02 direction threshold being a convenience). It does not describe error handling for invalid combinations or pagination, keeping it from a 5.

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?

Every sentence carries substantive content — metrics, parameter routing, caveats, disclaimer — with the metric inventory front-loaded. The weakness is structure: it is delivered as one dense run-on paragraph mixing invocation rules, output semantics and caveats, which raises parsing cost for an agent.

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?

For a five-parameter analytical tool with no annotations and no output schema, the description compensates well: it defines the returned fields, the scale of hhi, the direction labels, and the conditional outcomes. Remaining gaps are minor — invalid-input behavior and whether results are cached or read-only are not stated, though the read-only nature is strongly implied.

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 genuine meaning beyond the schema by tying flow to what is actually measured (supplying countries vs destinations), noting that month is effectively ignored for HS codes, and clarifying that reporter is unused with indicator. The indicator/reporter+code mutual exclusivity is reinforced rather than merely repeated.

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 states a specific computed resource: supplier concentration behind an indicator or HS code over the latest 12 months, enumerating the exact metrics returned (hhi, largest/top-three share, country count, direction label, main suppliers). An agent can immediately distinguish this from siblings like get_partners or get_ranking, which enumerate partners or rank entities rather than measuring concentration.

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?

It gives a clear use case ("questions about how concentrated the sources of a product are and whether they are concentrating or diversifying") and spells out the two mutually exclusive invocation paths, including defaults (import) and that exports measure destination concentration. It does not name an alternative tool for related questions (e.g., where to get the raw partner list), so it stops short of explicit routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TradeStats - customs trade statistics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?