Treasury Tic

Tic Major Treasury Holders

tic_major_treasury_holders

Read-onlyIdempotent

The "Major Foreign Holders of Treasury Securities" ranking from U.S. Department of the Treasury's Treasury International Capital (TIC) System, Major Foreign Holders of Treasury Securities table — the figure financial press cites as " holds $X of US Treasuries." Covers the ~20 largest individual foreign holders plus an "All Other" bucket, the grand total, and the foreign-official-sector split (central banks/governments vs. private holders), in USD billions. Pass "country" for one country's recent months; omit it for the full ranking in a given month (default: most recently published). Only the largest ~20 holders are broken out individually — a smaller holder is not in this table even though it may appear in tic_foreign_holdings. Answers "how much Treasury debt does China hold", "who are the top foreign holders of US government debt".

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": 5
    },
    "name": "tic_major_treasury_holders"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Ranking mode: how many countries to return (1-25, default 21, i.e. all of them). Country mode: how many recent months of history (1-13, default 13, the full window the table publishes).
`month`	No	YYYY-MM. Omit for the most recently published month.
`country`	No	One of the ~20 individually-broken-out countries, e.g. "Japan", "China". Omit for the full ranking.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it discloses the table's coverage limits, the USD-billions unit, the inclusion of an All Other bucket and foreign-official-sector split, and the critical caveat that smaller holders are excluded. It does not describe pagination or return shape, but that is a minor gap given the strong coverage disclosure.

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?

The description is front-loaded with the dataset identity and scope, then moves to usage instructions and limitations. It is slightly dense and repeats the table name, but every sentence contributes useful routing or scope information. It is appropriately sized for a data-lookup tool with no output schema.

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?

There is no output schema, so the description carries the burden of explaining return content and does so: USD billions, ~20 individual holders, All Other bucket, grand total, and official/private split. It also covers defaults, modes, and the sibling-tool exclusion rule. An agent has enough context to select and invoke this tool correctly.

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 description coverage is 100%, so the schema already explains limit, month, and country. The description adds meaningful semantic context by explaining that 'country' switches between country mode and ranking mode, and that omitting month defaults to the most recently published month. It reinforces how limit behaves differently across modes, which helps an agent invoke the tool correctly.

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 the exact dataset and resource: the Treasury International Capital 'Major Foreign Holders of Treasury Securities' ranking. It specifies the scope precisely, including the ~20 largest foreign holders, an All Other bucket, grand total, and official/private split in USD billions. This is specific verb+resource clarity and distinguishes the tool from the sibling tic_foreign_holdings.

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?

The description explicitly says to pass 'country' for one country's recent months and to omit it for the full ranking in a given month, with a stated default. It also gives a clear exclusion rule: only the largest ~20 holders are broken out individually, and a smaller holder is not in this table even though it may appear in tic_foreign_holdings. This directly routes the agent between this tool and its sibling.

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

All Treasury Tic 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.