U.S. tariffs (HTS), Schedule B codes, export statistics, party screening and FMC license checks.
Scored across 8 tools
Each tool has a distinct resource+action: Schedule B (export classification) vs HTS (import classification), product-level vs state-level stats, screening, and license lookup. The main soft spot is the search-vs-get pairing for tariffs (search_us_tariffs vs get_us_tariff) and the export/import classification pair, but the descriptions explicitly differentiate them.
All names use consistent snake_case verb_noun structure. The verbs vary for comparable lookup operations (find_schedule_b, find_us_exporters, search_us_tariffs, get_us_tariff), which is a minor inconsistency but still readable and reasonably predictable.
Eight tools is well-scoped for a U.S. trade data server, covering classification, tariffs, trade statistics, exporter directory, and compliance screening without bloat or gaps in count.
The surface covers export/import classification, duty rates, product- and state-level trade stats, exporter discovery, restricted-party screening, and FMC licensing — a broad, coherent set. Minor gaps exist (e.g., no dedicated tool to fetch a full profile for a specific listed exporter or to drill deeper into a single destination market), but core trade workflows are covered.
Search the official U.S. Census Bureau Schedule B (10-digit export classification used to file Electronic Export Information) by product words or by code prefix. Returns up to 50 codes with their official description and a link to each code's page (unit of quantity, when EEI is required, HS code used abroad, top U.S. export markets).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Product words (e.g. "frozen shrimp") or a Schedule B code prefix (e.g. "8703.23"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint, openWorldHint=false), so the bar is lower, and the description adds a concrete behavioral trait: a 50-result cap. It also enumerates what each returned record contains, going beyond what the annotations provide without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences, front-loaded with the core purpose and scope before the return-value summary. Every clause carries information; nothing is padded or redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by explaining the return shape (up to 50 codes, official description, per-code link, unit of quantity, EEI requirement, HS code, markets). For a single-parameter read-only lookup this gives the agent everything needed to call and interpret it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the single query parameter is already fully documented with the same examples. The description restates the product-words-or-code-prefix distinction but adds no syntax, formatting, or edge-case detail beyond the schema, matching the baseline-3 expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (Search) and a precisely scoped resource (the official U.S. Census Bureau Schedule B, a 10-digit export classification used to file EEI). The parenthetical definition of Schedule B clearly separates it from tariff/import siblings like search_us_tariffs and get_us_tariff, so an agent can distinguish it without opening menus.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It tells the agent the two query modes (product words or code prefix) which is genuinely useful context for invocation. However, it never states when to prefer this tool over siblings such as search_us_tariffs or how to handle ambiguous lookups, so usage is only implied rather than guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Fromerica directory of U.S. manufacturers and exporters by product. If no company is listed yet, returns the link where an importer can post a free request for quote that is shown to matching U.S. suppliers. Companies on the paid Pro plan are listed first and marked paid_placement=true.
| Name | Required | Description | Default |
|---|---|---|---|
| product | Yes | Product the buyer is looking for, e.g. "tractor parts". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/openWorldHint annotations, it discloses two non-obvious behaviors: results are ordered so paid Pro members appear first with paid_placement=true, and that a no-result search still returns an actionable RFQ link. The paid-placement disclosure is exactly the kind of ranking bias an agent should know about; more detail on result limits or pagination is the only gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences: purpose first, then the empty-result fallback, then the ranking caveat. Every sentence carries information an agent needs and nothing is repeated from the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and only one parameter, the description carries the burden of explaining returns, and it does so for the key fields (RFQ link, paid_placement flag). It remains silent on result volume, pagination, or whether queries are logged, which are minor omissions for this tool type.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single 'product' parameter is fully documented in the schema with an example. The description's 'by product' matches the schema without adding syntax or format guidance, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb+resource+filter: 'Search the Fromerica directory of U.S. manufacturers and exporters by product.' It names the platform, the entity type, and the search dimension, which clearly separates it from siblings like get_us_export_markets or find_schedule_b that deal with aggregate trade data rather than supplier lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description frames the use case (a buyer/importer looking for suppliers of a product) and explains the fallback path when nothing is listed: an RFQ link shown to matching suppliers. It does not name alternatives explicitly, but the sibling set is functionally distinct enough that the context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Official U.S. Census Bureau statistics for one product at the HS 4-digit level: total U.S. exports, the top destination countries with year-to-date change, and the states that ship the most.
| Name | Required | Description | Default |
|---|---|---|---|
| hs4 | Yes | HS 4-digit heading, e.g. "1201" (soybeans) or "8471". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool read-only, so the description doesn't need to repeat that. It adds behavioral context by specifying the exact data points returned (total exports, top countries, year-to-date change, states) and the authoritative Census source. It doesn't discuss pagination or data freshness, but with readOnlyHint covering safety, this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, well-organized sentence front-loads the authoritative scope ('Official U.S. Census Bureau statistics for one product at the HS 4-digit level') followed by a colon and a compact list of precisely what the tool returns. Every phrase earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read-only tool without an output schema, the description gives an agent enough information to decide and invoke: it names the required input type, the scope, and the output components. The only minor gap is the unspecified number of 'top' destinations and the exact time window for 'year-to-date', but these are unlikely to block correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, hs4, is fully documented in the schema with examples. The description reinforces that the tool works for one product at the HS 4-digit level, but adds no new meaning 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool's function: it provides official U.S. Census Bureau statistics for a single HS 4-digit product, including total exports, top destination countries with year-to-date change, and top shipping states. This precise breakdown distinguishes it from sibling tools like find_us_exporters or get_us_exports_by_state.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it—when a product-level view of export markets is needed—but it does not explicitly mention alternatives or state when not to use it. The overlap with get_us_exports_by_state (which also touches state export data) is not addressed, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Official U.S. Census Bureau export statistics for one U.S. state or territory (origin of movement): total exports for the last full year and year to date, rank among states, and the top destination countries and products.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | Two-letter state code (e.g. "TX") or state name (e.g. "Texas"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description need not repeat that. It adds value by specifying the data scope (origin of movement) and the specific statistics returned, which is useful behavioral context beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the purpose ('Official U.S. Census Bureau export statistics') and then enumerates the output details without waste. Every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is complete. It covers what data is returned, the geographic scope, and the data source, leaving no critical gaps for an agent to know how to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single 'state' parameter, so the schema already explains the format. The description does not add extra semantic detail beyond what the schema provides, aligning with the baseline of 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns official U.S. Census Bureau export statistics for a specific state or territory, listing the exact contents (totals, rank, top destinations/products). This distinguishes it from siblings like get_us_export_markets, which likely cover different angles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for state-level export data but does not explicitly mention alternatives or when not to use this tool. There is no comparison to siblings such as get_us_export_markets or find_us_exporters, leaving the agent to infer based on the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the official U.S. import duty rates for one HTS code (general, special and column 2), its description path, the date it was last checked against the official schedule, notes for chapter 99 provisions (additional duties, expired temporary reductions), and U.S. export figures for the product when available.
| Name | Required | Description | Default |
|---|---|---|---|
| hts_code | Yes | HTS code with dots, e.g. "8504.31.20.00" or "9903.88.03". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds value by revealing additional behaviors: it checks the official schedule, includes chapter 99 provisions, and notes that export figures are 'when available', which is useful context beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, information-dense sentence that front-loads the primary deliverable (duty rates). It includes multiple details compactly without redundancy, though it could be broken into clearer clauses. Overall, it is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has only one parameter, the schema fully describes it, and annotations cover the read-only nature. The description explains most return values (duty rates, description path, last-checked date, notes, export figures). It might not specify exact structure or pagination, but with full schema coverage, missing details are minor.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage, including a detailed description of hts_code with the expected format and examples. The tool description does not add new parameter-level semantics, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves official U.S. import duty rates for a single HTS code, listing the specific data fields (duty rates, description path, last-checked date, chapter 99 notes, export figures). It distinguishes itself from the sibling search_us_tariffs by focusing on one HTS code rather than searching.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it is for a single, specific HTS code while search_us_tariffs is for searching, providing implicit usage context. It does not explicitly state when NOT to use it (e.g., for multiple codes), but the singular focus is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check a company or person name against the U.S. Consolidated Screening List (Commerce, State and Treasury: OFAC SDN, BIS Entity List and others), refreshed daily. Returns possible matches with their source list and match strength. A match is not a legal determination, and no match does not mean the party is cleared.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Company or person name to check. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that: the list is 'refreshed daily' (freshness), it returns possible matches with source list and match strength (return behavior), and it clarifies that a match is not a legal determination and no match does not mean clearance (limits of the result).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the core action, then the return, then the legal caveat. Each sentence contributes; the parenthetical list enumeration is slightly dense but informative rather than wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter, read-only screening tool with no output schema, the description supplies the action, the source scope, the general return shape, and the interpretive caveat. What it omits – details on how 'match strength' is computed or result volume/pagination – is minor.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single 'name' parameter, so the description's 'company or person name to check' merely restates the schema. Per the baseline rule for high coverage, this is a 3 – no syntax, format, or edge-case guidance is added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource – checking a company or person name against the U.S. Consolidated Screening List – and even enumerates the constituent lists (OFAC SDN, BIS Entity List, etc.). The purpose is naturally distinct from the tariff/exporter siblings, but the description never names or contrasts a sibling tool, which is the only thing keeping it off a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The opening sentence implies when to use it (screening a party name), but there are no explicit when-to-use/when-not-to-use statements, no mention of alternatives, and no preconditions. Usage is left to inference from the purpose statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the official U.S. Harmonized Tariff Schedule (USITC, refreshed daily) by product words or by an HTS code prefix. Returns up to 20 tariff lines with their general, special and column 2 duty rates and a link to each code's page on Fromerica.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Product words (e.g. "solar panels") or an HTS code prefix (e.g. "8541" or "9903.88"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only behavior, so the description adds value by disclosing the daily refresh of data, the 20-result cap, and the specific output fields (general, special, and column 2 duty rates) plus links. This gives an agent a clear picture of what to expect beyond the annotation metadata.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action and scope, followed by output details. It contains no redundant phrases and every clause contributes to understanding the tool's behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With only one required parameter, no output schema, and annotations covering the read-only safety profile, the description sufficiently describes the return payload, result limit, and data source freshness. An agent has all the information needed to invoke and interpret the result correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully documents the single 'query' parameter with examples and semantics (product words or HTS prefix), providing 100% coverage. The description restates the same input types in prose without adding new meaning, so it remains at the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Search'), a specific resource ('official U.S. Harmonized Tariff Schedule'), and the input forms (product words or HTS prefix). It also describes the output shape (up to 20 tariff lines with duty rates), which distinguishes it from the singular-lookup sibling get_us_tariff.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (when you need to find tariff data by product words or HTS code prefix), but it does not explicitly compare against siblings or state when not to use it. No alternatives or exclusions are mentioned, so the guidance is limited to implied context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether a company appears on the Federal Maritime Commission's list of licensed and bonded Ocean Transportation Intermediaries (ocean freight forwarders and NVOCCs), by company name or license number. Returns license number, type, location and renewal date.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Company name (e.g. "Young Sea Cargo") or FMC license number. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds the return fields (license number, type, location, renewal date), which is useful, but it does not disclose potential caveats like data freshness, match behavior, or error conditions. With annotations covering safety, this is adequate but not exceptional.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the purpose, the matching criteria, and the returned fields with no redundancy or filler. Every word contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter, no output schema, and simple look-up behavior, the description adequately covers the core aspects: what it checks, how to query, and what is returned. It does not address edge cases like not-found or multiple matches, but these are minor for such a simple tool and could be inferred from the described behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema description ('Company name (e.g. "Young Sea Cargo") or FMC license number.') already fully defines the query parameter. The tool description only restates this ('by company name or license number') without adding new meaning, so it stays at the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('Check') and resource ('FMC list of licensed and bonded Ocean Transportation Intermediaries'), and clarifies it operates by company name or license number. It is clearly distinct from the sibling tools which focus on exports, tariffs, and restricted parties, so an agent can immediately identify its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states what the tool does but offers no explicit guidance on when to use it versus alternatives, nor any exclusions. While the purpose is clear enough to infer, it does not mention, for example, that restricted-party screening should use screen_restricted_party, leaving the routing to the agent's inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_schedule_bfind_us_exportersget_us_export_marketsget_us_exports_by_stateget_us_tariffscreen_restricted_partysearch_us_tariffsverify_fmc_licenseUS import duty and HTS codes from the official USITC schedule, plus Section 301 China status. Free.
US import tariff lookup against the official USITC Harmonized Tariff Schedule
Classify, validate & verify HS codes and access tariff compliance data for cross-border trade
HTS MCP — US import tariff rates via the USITC Harmonized Tariff Schedule.
Add one secure layer between your agents and this server.