Sanctions & Tariff Lookup

Compare the U.S. duty on one HTS line across countries of origin

compare_origins

Read-onlyIdempotent

Computes the same duty total as duty_stack for one 8- or 10-digit HTS line across up to 30 countries of origin and returns them sorted from the lowest total, each with its base rate, the Chapter 99 headings applied and the number of open questions. Without "origins" it compares 20 large sources of U.S. imports. Each row uses default assumptions (no trade-agreement preference claimed, no special use).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "hts_code": "<hts_code>"
    },
    "name": "compare_origins"
  }
}

Input Schema

Name	Required	Description
`answers`	No	Optional answers applied to every origin, by question id, e.g. {"preference": true}.
`origins`	No	Countries of origin to compare: ISO 3166-1 alpha-2 codes or English names, e.g. ["CN", "VN", "MX"].
`hts_code`	Yes	HTS number with 8 or 10 digits, dotted or not, e.g. "9403.60.80".
`ad_valorem_equivalent_pct`	No	Optional ad valorem equivalent, in percent, of a specific or compound column 1 rate.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description rightly spends its words elsewhere: it discloses the default assumptions (no trade-agreement preference claimed, no special use), the sort order, and the per-row contents including 'number of open questions'. It does not say what happens if the HTS line is invalid or whether 30 origins is slow, leaving minor behavioral gaps.

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?

Three sentences, front-loaded with the compute-and-sort behavior, then the fallback default, then the assumptions caveat. The first sentence is long and chains several clauses, but every clause carries useful information and nothing is redundant.

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?

With no output schema and a nested 'answers' object, the description does a solid job by enumerating the returned fields and the assumption defaults that shape them. The main remaining gap is how an agent should act on the reported 'open questions' — whether to re-invoke with 'answers' — which is left implicit.

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, but the description adds genuinely non-schema meaning: when 'origins' is omitted the tool compares 20 large U.S. import sources, and rows are evaluated under default assumptions that 'answers' would override. It does not explain how the shape of 'answers' maps to the reported 'open questions', which keeps it below 5.

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 and resource — computes the same duty total as duty_stack for one 8- or 10-digit HTS line across up to 30 origins — and names the sibling it is analogous to, so the agent can tell it apart from duty_stack and hts_rate. It also specifies the ordering (lowest total first) and the per-row payload.

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?

The phrase 'the same duty total as duty_stack ... across up to 30 countries of origin' clearly establishes the multi-origin comparison case versus the single-stack sibling, and the omitted-'origins' fallback of 20 large sources is spelled out. There is no explicit 'do not use when' or a named single-origin alternative, so it stops short of full routing guidance.

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

All Sanctions & Tariff Lookup 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?