MingXi Export Control

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It mentions 'auto-route' but does not explain how routing works, whether it is read-only, what happens on no results, or how results are combined across datasets. This is a significant gap for a tool that spans multiple datasets.

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 concise sentences, with the core purpose stated first and the usage guidance second. No filler or redundant content; every word contributes value.

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 that routes across all datasets, the description is too thin. It does not mention the output schema's role (though it exists), nor does it cover expected behavior like result aggregation, error handling, or performance constraints. The presence of an output schema helps return-value clarity, but behavioral context is lacking.

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 0%, so the description must compensate. It gives an example for 'keyword' but does not explicitly define 'keyword' or 'limit'. The schema itself has titles and types, but without any textual explanation of the parameters' nuances, the description adds minimal value beyond the schema.

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 'Auto-route query across all datasets', which clearly identifies the verb (route) and resource (all datasets). It also names the intended use case (ambiguous searches) with concrete examples, distinguishing it from sibling tools that target specific datasets.

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?

Explicitly says 'Best for ambiguous searches' and gives examples, directly guiding when to use this tool over alternatives. Though it doesn't name specific siblings, the context makes the contrast clear, satisfying the when-to-use criterion.

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

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

With no annotations provided, the description carries the full transparency burden. It discloses that the tool searches two distinct catalogues, which is useful behavioral context, and the verb 'Search' implies a read-only operation. However, it does not explicitly state read-only behavior, how results from the two catalogues are combined, or any edge-case behavior.

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 tight sentences with the core function front-loaded and usage details following. Every clause carries useful information, with no redundancy or filler.

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 description provides the essential information for selecting and invoking a read-style search tool, and an output schema exists to define the return shape. It lacks explicit guidance on when to choose this tool over siblings and does not clarify how the two-catalogue search behaves, leaving some selection and expectation-setting burden on the agent.

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 0%, so the description must compensate. It meaningfully defines the keyword parameter by specifying acceptable inputs (HS code, ECCN code, or technical description, with the example 1C351), but it does not mention the limit parameter at all. The limit parameter is standard and has a schema default, so the gap is moderate rather than severe.

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 precise resource ('dual-use items & technologies'), then further names the two underlying datasets: the 2026 HS-based license catalogue and the ECCN-coded export control list. This level of specificity clearly distinguishes it from sibling tools like query_tariff or query_prohibited, even without explicitly naming them.

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 provides input-format guidance ('Use HS code, ECCN code (e.g. 1C351), or technical description') but does not state when to use this tool versus its siblings, nor does it mention any exclusions or alternatives. An agent must infer selection entirely from the 'dual-use' wording in the purpose statement.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose a key trait: results are 'merged across lists', which tells the agent it searches multiple lists. However, it does not mention read-only semantics, pagination, rate limits, or behavior on empty results. Since it's a search tool, the read-only nature is implied, but not explicit. The description adds some behavioral context but not enough for a tool with zero annotation support.

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 with no fluff. It front-loads the action and resource, then adds a usage hint. Every word earns its place, and the structure is efficient and scannable.

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 2 parameters, no annotations, and no schema descriptions, the description is too thin. It omits the meaning of 'limit', gives no selection guidance against siblings, and doesn't mention output shape (though an output schema exists). The description covers only the keyword and the merged-lists behavior, leaving significant gaps that an agent must guess.

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 0%, so the description must compensate for both parameters. The description explains the keyword parameter indirectly ('Use company or individual name') but says nothing about the 'limit' parameter, its purpose, or its default behavior. The agent is left to infer that limit controls result count, which is not stated. Given the zero coverage, this is a significant gap.

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 verb 'Search' and the resource 'export control / sanctions entity lists', and adds the scope 'merged across lists'. It also gives a hint about input ('company or individual name'). It does not explicitly distinguish from sibling tools like query_dualuse or query_prohibited, but the resource type is specific enough that an agent can infer it's for entity lists rather than other categories. A 4 is appropriate since it's clear but lacks explicit sibling differentiation.

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 gives no guidance on when to use this tool versus the sibling tools (query_any, query_dualuse, query_fta_origin, query_prohibited, query_tariff). It only hints at input type, not selection criteria or exclusions. An agent would have to infer from the name and resource that this is for entity searches, but the description doesn't state when to choose it over alternatives, so the usage guidance is minimal.

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

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

With no annotations, the description carries the behavioral burden. It discloses the query input modes and agreement coverage, but it does not explain matching behavior (e.g., partial HS codes, exact matches), how 'limit' affects results, or any other operational behavior.

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?

One front-loaded sentence states the action, resource, coverage, and input method with no filler. Every element 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 two-parameter search tool with an output schema, the description is mostly adequate but leaves gaps: no guidance on HS code format or matching semantics, no use of limit, and no explicit sibling differentiation. Output shape is reasonably covered by the existence of an output schema.

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 0%, so the prose must explain the parameters. It does explain 'keyword' as an HS code or product keyword, but 'limit' is never mentioned in the description; only the schema default (10) is visible.

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 names a specific verb ('Search'), a concrete resource ('FTA product-specific rules of origin'), a coverage list ('25 agreements incl. RCEP, ASEAN, Korea'), and the input modes ('HS code or product keyword'). This makes it easy to distinguish from sibling tools such as query_tariff or query_dualuse.

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 the tool is for looking up FTA origin rules by HS code or keyword, which gives some usage context. It does not explicitly state when to prefer this tool over siblings or list exclusions, so an agent must infer the boundary between this and query_tariff.

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

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

No annotations are provided, so the description carries the full burden. It conveys that the operation is a search and adds the behavioral nuance 'all batches,' but it does not explicitly state read-only behavior, result limits, pagination, or any potential side effects. The query nature makes major side effects unlikely, but the disclosure is thin.

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 with no filler. It states the action, the resource, the scope, and the search method efficiently, so every word 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?

Given the simplicity of the tool (two parameters, one required) and the existence of an output schema, the description covers the core calling context: what to search, the catalogue scope, and the accepted key types. It does not address limit semantics or explicitly route around sibling tools, but those are relatively minor gaps for a simple query tool.

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 0%, so the description must compensate. It adds meaningful semantics for the keyword parameter by saying searches can be by keyword or HS code, but it says nothing about the limit parameter, whose meaning is only inferable from its title and default value.

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 uses a specific verb ('Search') and a specific resource ('prohibited import/export goods catalogues'), and it adds the scope 'all batches.' The word 'prohibited' clearly differentiates this tool from siblings like query_dualuse, query_any, and query_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 domain is implied by 'prohibited' but there is no explicit guidance about when to use this tool versus its siblings, no exclusion conditions, and no mention of the alternative query tools. An agent must infer the intended use case from the resource name rather than being told.

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

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

With no annotations, the description carries the full burden. It discloses that it returns MFN/provisional/agreement/preferential/general rates, which is useful behavioral information. However, it does not mention any limitations (e.g., only 2026 data, no historical years), potential errors, or whether it is read-only (though 'Search' implies read-only). It also includes an unclear 'dataset optional' phrase that does not map to the schema parameters.

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 concise, with two clear sentences and a short fragment. It front-loads the primary purpose and includes return value information. The 'dataset optional' fragment is a minor distraction and could be removed for clarity, but overall the structure 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 is a simple query with keyword and limit, and an output schema exists. The description covers the core purpose and return types, but it does not mention any nuances such as the fact that it only covers 2026 or that results might be limited by the 'limit' parameter. The 'dataset optional' discrepancy also suggests a possible mismatch between the description and the actual schema, leaving some ambiguity.

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 0%, so the description must compensate. It explains the 'keyword' parameter as 'HS code or keyword', but it does not explain the 'limit' parameter at all. Additionally, the description mentions 'dataset optional' which does not correspond to any parameter in the schema, creating confusion. This is insufficient given the lack of schema descriptions.

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 action ('Search'), the specific resource ('China 2026 import tariff schedule'), and the search criteria ('by HS code or keyword'). It also lists the types of rates returned, which distinguishes it from sibling tools like query_dualuse or query_prohibited, which have different purposes.

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 this tool is for tariff queries, but it does not explicitly state when to use it over the sibling tools or mention any exclusions. There is no guidance like 'use this for tariff rate lookups' or 'do not use for other trade restrictions.' The name and resource make the purpose clear, but explicit usage context is missing.

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