USTariffRates

AD/CVD cash-deposit rate

adcvd_cash_deposit

Access: API key required. Current CBP cash-deposit rate for one AD/CVD case, exporter, producer and entry date, from reviewed CBP instruction histories, with the governing CBP message, its effective dates and content hash. Named exporter/producer combinations and company rates come first; the all-others rate applies only when both parties are named and neither has its own rate. A combination the instruction excludes from the order is answered excluded_from_order. A suspended investigation (no order; CBP liquidates entries without regard to the duties) is refused with reason investigation_suspended_no_cash_deposit and the CBP message. Refusals state the reason. Scope is not evaluated; deposits are estimates, never final assessed duties.

Input Schema

Name	Required	Description
`as_of`	Yes	ISO date in YYYY-MM-DD form
`country`	No	ISO-2 country code of origin
`exporter`	No
`producer`	No
`case_number`	Yes
`cbp_case_number`	No	CBP case number of the order's class, for an order CBP files under one number per class (A-570-803: A-570-201 hammers and sledges, A-570-202 bars and wedges, A-570-203 picks and mattocks, A-570-204 axes and adzes).
`exporter_country`	No	ISO-2 country code of origin
`customs_value_usd`	No
`duty_free_importation_approved_on`	No	Date Commerce notified the requester that it permits this merchandise to enter free of the order's duties under a temporary duty-free importation (19 CFR 358.103(b)). Declare only for merchandise identified in an approved request; otherwise the current rates apply.
`revocation_certifications_maintained`	No	Whether the importer and the exporter maintain the certifications, with supporting documentation, that a partial revocation of the order requires for no cash deposit to be required. Asked only for a producer and exporter combination such a revocation covers.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 31, 2026

addedInput schema / properties / cbp_case_number

Added value: +{
+  "description": "CBP case number of the order's class, for an order CBP files under one number per class (A-570-803: A-570-201 hammers and sledges, A-570-202 bars and wedges, A-570-203 picks and mattocks, A-570-204 axes and adzes).",
+  "pattern": "^[AC]-\\d{3}-\\d{3}$",
+  "type": "string"
+}

addedInput schema / properties / duty_free_importation_approved_on

Added value: +{
+  "$ref": "#/properties/as_of",
+  "description": "Date Commerce notified the requester that it permits this merchandise to enter free of the order's duties under a temporary duty-free importation (19 CFR 358.103(b)). Declare only for merchandise identified in an approved request; otherwise the current rates apply."
+}

addedInput schema / properties / revocation_certifications_maintained

Added value: +{
+  "description": "Whether the importer and the exporter maintain the certifications, with supporting documentation, that a partial revocation of the order requires for no cash deposit to be required. Asked only for a producer and exporter combination such a revocation covers.",
+  "type": "boolean"
+}

First observedOct 26, 2026

TDQS

A3.9/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses API-key auth, the named-combination vs all-others precedence, the excluded_from_order outcome, the investigation_suspended_no_cash_deposit refusal with the governing CBP message, and that returns include effective dates and a content hash. It also frames the output as an estimate, never a final assessed duty.

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 dense but front-loaded, opening with access requirements and the core return value before edge-case rules. Sentences are long but each carries substantive rules; little is wasted for a tool this conditional.

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 10-parameter, annotation-free lookup with no output schema, the description covers the key decision branches and failure modes. Gaps remain around how customs_value_usd affects the answer and the exact response shape, but the essential behavioral contract is present.

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 coverage is 60%, so the description must add value and it does for exporter/producer combinations and the as_of entry date. But it says nothing about customs_value_usd or cbp_case_number (the latter documented only in the schema), leaving a meaningful share of the 10 parameters unexplained beyond structured fields.

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?

States a specific verb and resource: the current CBP cash-deposit rate for one AD/CVD case, exporter, producer and entry date, sourced from reviewed CBP instruction histories. The AD/CVD specificity makes it distinguishable from generic siblings like calculate_duty, but no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the resolution rules (named combinations first, all-others only when both parties are named with no own rate) and refusal cases, which guides correct invocation. However, it never says when to reach for this tool versus calculate_duty or screen_import_requirements; scope handling ('Scope is not evaluated') only implies that scope questions belong elsewhere.

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

All USTariffRates 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?