Skip to main content
Glama

usitc-tariffs-mcp-server

Research Chapter 99 additional-duty evidence

usitc_check_additional_duties
Read-onlyIdempotent

Find Chapter 99 candidate headings and source references for an exact eight- or ten-digit commodity number. Coverage is partial and empty candidates never establish clearance. Use candidates, evidence with a returned candidateCode, or unmapped views; follow returned noteId and noteCursor for complete source passages. Country comparisons retain unknown and different-country evidence. No applicability, current legal status, exclusions, stacking or combined duties are determined.

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": {
      "code": "<code>"
    },
    "name": "usitc_check_additional_duties"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesExact eight- or ten-digit base commodity number, bare or conventionally dotted; Chapter 99 input is invalid.
viewNoOne result collection; evidence requires candidateCode.candidates
limitNoDefault 10; a larger value returns at most 100 items and says so. Keep the same limit when continuing with a cursor.
cursorNoOpaque nextCursor from the same tool with identical arguments.
noteIdNoReturned supporting passage identifier; cannot combine with candidateCode, cursor or a nondefault view.
noteCursorNopage.nextCursor returned by a noteId page; requires the same noteId and original selectors.
countryCodeNoAssigned ISO alpha-2 country; comparison only, never sent upstream.
candidateCodeNoReturned Chapter 99 candidate number, only with view evidence.

Output Schema

NameRequiredDescriptionDefault
codeNoCanonical exact commodity number.
pageNoComplete selected-collection pagination.
viewNoOnly the selected collection is included.
errorNoPresent when the call failed. Absent on success.
foundNoWhether that exact base number exists; a statistical miss never falls back.
noticeNoActionable next call for this particular empty result, followed by a disclosure when a requested limit above 100 was clamped.
sourceNoSource provenance.
noticesNoPersistent source and coverage limitations.
releaseNoEdition checked for this result.
baseLineNoBase-line identification without duplicating the full source row; first candidates page only.
coverageNoPartial coverage, never a completeness or clearance claim. The first candidates page (no cursor) carries the measured facts; every other page carries status only. Parser limitations are listed in notices.
evidenceNoSelected complete evidence references for one candidate.
guidanceNoActionable follow-up for an exact base miss.
nextCallNoExact selected-collection continuation arguments.
notesPageNoComplete passage retrieval, without candidate arrays.
sourceUrlNoChapter 99 rate export URL that supplied every candidate description and published rate; on candidates pages.
candidatesNoSelected whole candidates, without nested evidence passages.
totalCountNoComplete locally filtered item count.
notComputedNoLegal, qualification and arithmetic questions not determined.
candidateCodeNoSelected candidate in evidence view.
countryFilterNoFactual prioritization counts over the full candidate collection; first candidates page only.
normalizationNoNotes decoding and normalization provenance, on the first candidates page and noteId pages; absent when notes were not searched.
collectionTotalsNoComplete collection totals before page selection; first candidates page only.
unmappedEvidenceNoSelected unmatched references, including unresolved compiler notices.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed34 schema fields changed
    • addedInput schema / properties / candidateCode / pattern
      Added value: +"^\\s*(?:(?:\\d{4}(?:\\d{2}){0,3}|\\d{4}\\.\\d{2}(?:\\.\\d{2}){0,2}|\\d{4}\\.\\d{2}\\.\\d{4})\\s*)?$"
    • addedInput schema / properties / code / pattern
      Added value: +"^\\s*(?:\\d{4}(?:\\d{2}){0,3}|\\d{4}\\.\\d{2}(?:\\.\\d{2}){0,2}|\\d{4}\\.\\d{2}\\.\\d{4})\\s*$"
    • addedInput schema / properties / countryCode / pattern
      Added value: +"^\\s*(?:[A-Za-z]{2}\\s*)?$"
    • changedInput schema / properties / limit / default
      Previous value: -25New value: +10
    • 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 10; a larger value returns at most 100 items and says so. Keep the same limit when continuing with a cursor."
    • changedInput schema / properties / noteCursor / description
      Previous value: -"Returned nextNoteCursor; requires the same noteId and original selectors."New value: +"page.nextCursor returned by a noteId page; requires the same noteId and original selectors."
    • changedOutput schema / properties / baseLine / description
      Previous value: -"Base-line identification without duplicating the full source row."New value: +"Base-line identification without duplicating the full source row; first candidates page only."
    • removedOutput schema / properties / candidates / items / properties / sourceUrl
      Removed value: -{
      -  "description": "Exact Chapter 99 export source URL supplying the rate row.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / candidates / items / required
      Previous value: -[
      -  "code",
      -  "headingResolved",
      -  "sourceUrl",
      -  "evidenceCount",
      -  "compilerNoticeCount",
      -  "evidenceFollowUp",
      -  "countryRelation",
      -  "legalStatus"
      -]New value: +[
      +  "code",
      +  "headingResolved",
      +  "evidenceCount",
      +  "compilerNoticeCount",
      +  "evidenceFollowUp",
      +  "countryRelation",
      +  "legalStatus"
      +]
    • changedOutput schema / properties / collectionTotals / description
      Previous value: -"Complete collection totals before page selection."New value: +"Complete collection totals before page selection; first candidates page only."
    • changedOutput schema / properties / countryFilter / description
      Previous value: -"Factual prioritization counts over the full candidate collection."New value: +"Factual prioritization counts over the full candidate collection; first candidates page only."
    • changedOutput schema / properties / coverage / description
      Previous value: -"Partial coverage facts, never a completeness or clearance claim."New value: +"Partial coverage, never a completeness or clearance claim. The first candidates page (no cursor) carries the measured facts; every other page carries status only. Parser limitations are listed in notices."
    • removedOutput schema / properties / coverage / properties / limitations
      Removed value: -{
      -  "description": "Measured and permanent parser limitations.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • changedOutput schema / properties / coverage / properties / sourceDigest / description
      Previous value: -"Chapter 99 notes byte digest; empty when notes were not searched."New value: +"First 16 hex of the Chapter 99 notes byte digest; empty when notes were not searched."
    • changedOutput schema / properties / coverage / properties / status / description
      Previous value: -"Permanent first-version grammar limitation."New value: +"Always partial: the supported grammar covers part of the notes, so no page, empty or not, establishes clearance from additional duties."
    • changedOutput schema / properties / coverage / required
      Previous value: -[
      -  "status",
      -  "parserVersion",
      -  "sourceDigest",
      -  "supportedGrammar",
      -  "totalNoteBlocks",
      -  "parsedListBlocks",
      -  "unresolvedReferenceBlocks",
      -  "ambiguousBlocks",
      -  "unmappedEvidenceCount",
      -  "unmappedFollowUp",
      -  "limitations"
      -]New value: +[
      +  "status"
      +]
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_code`: Identifier is not an exact eight- or ten-digit base commodity number. `invalid_country`: Country is not an assigned ISO alpha-2 value. `invalid_selector`: Evidence, passage and collection selectors cannot be combined as requested. `invalid_cursor`: Cursor is malformed or bound to different arguments. `cursor_expired`: Index or base snapshot expired, was evicted, or changed edition. `release_changed`: Edition changes twice during complete source assembly. `invalid_hierarchy`: Complete base heading cannot establish safe ancestry. `notes_structure_changed`: Required Chapter 99 structure is missing or cannot be decoded. `note_not_found`: Passage does not belong to this commodity query, source digest or edition. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_code`: code is not eight or ten digits or names a Chapter 99 number, or candidateCode is not eight digits. `invalid_country`: Country is not an assigned ISO alpha-2 value. `invalid_selector`: Evidence, passage and collection selectors cannot be combined as requested. `invalid_cursor`: Cursor is malformed or bound to different arguments. `cursor_expired`: Index or base snapshot expired, was evicted, or changed edition. `release_changed`: Edition changes twice during complete source assembly. `invalid_hierarchy`: Complete base heading cannot establish safe ancestry. `notes_structure_changed`: Required Chapter 99 structure is missing or cannot be decoded. `note_not_found`: Passage does not belong to this commodity query, source digest or edition. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / evidence / items / properties / matchLevel / description
      Previous value: -"Exact, verified parent or narrower statistical reference."New value: +"Exact, verified parent or narrower statistical reference; absent on a footnote from an ancestor row that is not the inherited rate source."
    • changedOutput schema / properties / evidence / items / properties / matchedCode / description
      Previous value: -"Exact commodity code mentioned; absent for unresolved compiler scope."New value: +"Matched commodity code in canonical dotted form (NNNN.NN.NN or NNNN.NN.NN.NN); absent for unresolved compiler scope."
    • removedOutput schema / properties / evidence / items / properties / passageId
      Removed value: -{
      -  "description": "Complete normalized passage identifier.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / evidence / items / properties / sourceCode / description
      Previous value: -"Referenced Chapter 99 code; absent when unresolved."New value: +"Referenced Chapter 99 code in canonical dotted form (9903.NN.NN), equal to its candidate code; absent when unresolved."
    • changedOutput schema / properties / normalization / description
      Previous value: -"Notes decoding and normalization provenance; absent when notes were not searched."New value: +"Notes decoding and normalization provenance, on the first candidates page and noteId pages; absent when notes were not searched."
    • removedOutput schema / properties / notesPage / properties / fragments / items / properties / passageId
      Removed value: -{
      -  "description": "Complete normalized passage identifier.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / notesPage / properties / fragments / items / required
      Previous value: -[
      -  "passageId",
      -  "fragmentIndex",
      -  "fragmentCount",
      -  "text"
      -]New value: +[
      +  "fragmentIndex",
      +  "fragmentCount",
      +  "text"
      +]
    • changedOutput schema / properties / notesPage / properties / nextCall / description
      Previous value: -"Exact passage continuation arguments."New value: +"Exact passage continuation arguments, with page.nextCursor as noteCursor; every omitted fragment remains reachable."
    • removedOutput schema / properties / notesPage / properties / nextNoteCursor
      Removed value: -{
      -  "description": "Next fragment page; every omitted fragment remains reachable.",
      -  "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."
    • addedOutput schema / properties / sourceUrl
      Added value: +{
      +  "description": "Chapter 99 rate export URL that supplied every candidate description and published rate; on candidates pages.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / unmappedEvidence / items / properties / matchLevel / description
      Previous value: -"Exact, verified parent or narrower statistical reference."New value: +"Exact, verified parent or narrower statistical reference; absent on a footnote from an ancestor row that is not the inherited rate source."
    • changedOutput schema / properties / unmappedEvidence / items / properties / matchedCode / description
      Previous value: -"Exact commodity code mentioned; absent for unresolved compiler scope."New value: +"Matched commodity code in canonical dotted form (NNNN.NN.NN or NNNN.NN.NN.NN); absent for unresolved compiler scope."
    • removedOutput schema / properties / unmappedEvidence / items / properties / passageId
      Removed value: -{
      -  "description": "Complete normalized passage identifier.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / unmappedEvidence / items / properties / sourceCode / description
      Previous value: -"Referenced Chapter 99 code; absent when unresolved."New value: +"Referenced Chapter 99 code in canonical dotted form (9903.NN.NN), equal to its candidate code; absent when unresolved."
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses the important limits: partial coverage, empty results proving nothing, country comparisons retaining unknown and different-country evidence, and the explicit disclaimer that no applicability, legal status, exclusions, stacking, or combined duties are determined. For a research tool that returns evidence rather than answers, those caveats are exactly what an agent needs.

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?

Information is front-loaded and nearly every clause carries content, with no filler. A few sentences are so compressed, such as 'Country comparisons retain unknown and different-country evidence,' that the meaning is not immediate on first read.

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 an output schema present it need not explain return values, and it does cover the key caveats and chaining behavior for an eight-parameter research tool. The only shortfall is that it does not position the tool against the sibling lookups an agent might reach for instead.

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%, so every parameter is already documented, including the view enum, the candidateCode dependency, and the noteCursor chaining rules. The description restates some of these relationships but adds no format or syntax detail beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: find Chapter 99 candidate headings plus source references for an exact eight- or ten-digit commodity number. That is concrete enough to separate it from the lookup and browse siblings, though it never names an alternative outright.

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 prescribes the workflow clearly: use candidates, evidence with a returned candidateCode, or unmapped views, then follow noteId and noteCursor for complete passages. It also warns that coverage is partial and empty candidates never establish clearance. What is missing is explicit routing against siblings such as the duty-rate lookup.

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.