Skip to main content
Glama

usitc-tariffs-mcp-server

Search published HTS classifications

usitc_search_hts
Read-onlyIdempotent

Search published USITC descriptions or complete HTS code prefixes in source order. codePrefix keeps only matches under a chapter or code before counting and paging. Matches are flat published rows with unresolved rates; call usitc_get_heading for legal ancestry and usitc_lookup_duty_rate for exact base rate columns. Follow nextCursor with identical arguments for all remaining matches.

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": {
      "query": "<query>"
    },
    "name": "usitc_search_hts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDefault 25; a larger value returns at most 100 items and says so. Keep the same limit when continuing with a cursor.
queryYesNonblank commodity text or an HTS code prefix; preserve leading zeros.
cursorNoOpaque nextCursor from the same tool with identical arguments.
codePrefixNoKeep only matches whose published number starts with this two-digit chapter or four-, six- or eight-digit code, bare or dotted; blank means omitted.

Output Schema

NameRequiredDescriptionDefault
pageNoComplete matching collection and continuation.
rowsNoComplete source rows selected for this page.
errorNoPresent when the call failed. Absent on success.
queryNoNormalized query actually sent to USITC.
noticeNoActionable next call for this particular empty result, followed by a disclosure when a requested limit above 100 was clamped.
sourceNoSource provenance.
contextNoFlat matches without reconstructed ancestry.
noticesNoPersistent source and coverage limitations.
releaseNoEdition checked for this result.
codePrefixNoCanonical code prefix applied before counting; absent when none was supplied.
totalCountNoComplete locally filtered item count.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / codePrefix
      Added value: +{
      +  "description": "Keep only matches whose published number starts with this two-digit chapter or four-, six- or eight-digit code, bare or dotted; blank means omitted.",
      +  "pattern": "^\\s*(?:(?:\\d{2}|\\d{4}(?:\\d{2}){0,2}|\\d{4}\\.\\d{2}(?:\\.\\d{2})?)\\s*)?$",
      +  "type": "string"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Requested items as a positive safe integer; effectiveLimit discloses clamping to at most 100, and pages may be byte limited. Keep the same requested limit for continuation."New value: +"Default 25; a larger value returns at most 100 items and says so. Keep the same limit when continuing with a cursor."
    • removedInput schema / properties / query / minLength
      Removed value: -1
    • addedInput schema / properties / query / pattern
      Added value: +"\\S"
    • addedOutput schema / properties / codePrefix
      Added value: +{
      +  "description": "Canonical code prefix applied before counting; absent when none was supplied.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Actionable next call for this particular empty result."New value: +"Actionable next call for this particular empty result, followed by a disclosure when a requested limit above 100 was clamped."
    • removedOutput schema / properties / page / properties / budgetLimited
      Removed value: -{
      -  "description": "True when the complete reply byte budget reduced this page.",
      -  "type": "boolean"
      -}
    • changedOutput schema / properties / page / properties / effectiveLimit / description
      Previous value: -"Applied item ceiling after clamping to 100."New value: +"Requested limit after clamping to 100; every page but the last is full."
    • removedOutput schema / properties / rows / items / properties / nodeId
      Removed value: -{
      -  "description": "Release and source-digest-local node identifier.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / rows / items / required
      Previous value: -[
      -  "nodeId",
      -  "sourceOrdinal",
      -  "indent",
      -  "description",
      -  "publishedRates",
      -  "sourceFields",
      -  "ratesResolved"
      -]New value: +[
      +  "sourceOrdinal",
      +  "indent",
      +  "description",
      +  "publishedRates",
      +  "sourceFields",
      +  "ratesResolved"
      +]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover safety (readOnly, idempotent, openWorld), and the description adds genuinely new behavior: results are in source order, codePrefix filters before counting and paging (so counts/pages differ from unfiltered searches), and rows carry unresolved rates. The pagination contract with cursors is spelled out rather than left implicit.

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?

Four tight sentences, front-loaded with the search capability, then narrowing to filtering, result shape, sibling escape hatches, and pagination. No filler, though the dense packing of cursor rules slightly muddies a first read.

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?

For a paginated search with an output schema already defining return values, the description covers everything an agent needs: filter-vs-pagination ordering, result row semantics, sibling routing, and cursor continuation. Nothing material is missing.

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 would be 3, but the description adds real semantics the schema does not convey: codePrefix is applied before counting and paging, and continuation requires identical arguments (including limit). That ordering detail materially changes how results are interpreted.

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 ('Search') plus the exact resource ('published USITC descriptions or complete HTS code prefixes') and even the ordering ('in source order'). It is distinguishable at a glance from usitc_get_heading and usitc_lookup_duty_rate, which it names.

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?

Gives an explicit routing rule: this tool returns flat published rows with unresolved rates, and the agent should call usitc_get_heading for legal ancestry or usitc_lookup_duty_rate for exact base rate columns. It also states the continuation rule ('Follow nextCursor with identical arguments'), covering the when and the how.

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.