Trade Evidence

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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered; the description adds genuinely new behavioral detail beyond them: the cost ('spends one search'), and the two-tier coverage model — exhaustive counting for all sellers but detailed classification only for up to 10 named refs and top listers. That sampling limit is exactly the kind of thing an agent needs to interpret results correctly. It stops short of describing pagination or response shape.

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?

It is compact and the core scope leads, but the prose is dense and telegraphic, cramming counting behavior, detail tiers, certificate categories, and cost into two overloaded sentences. The cost note ('Spends one search') is buried at the very end where it is most likely to be skimmed past.

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?

There is no output schema, so the description carries the burden of indicating what comes back, and it largely does: per-rule counts, per-exhibitor classification (matching certificate, claimed only, foreign mark or lab name only), and which rules fall on the importer. Enough to call it correctly and interpret the gist, though the exact result shape stays loose.

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%, so both parameters are already documented, and the schema itself explains the refs fallback ('Leave out to check the ones that list the most'). The description reinforces this by noting 'up to 10 named exhibitors and the others that list the most,' but adds no new syntax, format, or constraint information beyond the schema. Baseline 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 is specific about the operation and its scope: it matches each US rule's required paperwork against every exhibitor selling a product, returning per-rule counts plus a detailed subset. The verb and resource are identifiable (check exhibitor paperwork coverage for a product), though the opening sentence ('Who lists the paperwork each US rule for a product asks for') is grammatically tangled and slows comprehension. It implicitly distinguishes itself from us_requirements (the rules themselves) but never names that sibling.

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?

Usage context is implied rather than stated: 'Spends one search' signals this is a costly call to use deliberately, and the schema's mention of refs from search_listings implies a prerequisite workflow. However, the description never says when to use check_fit versus us_requirements, nor what to do when results are empty. The agent must infer the call sequence from the schema.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful behavioral context by stating the search-cost implication and the 5-exhibitor cap.

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 tightly packed sentences: the first front-loads the core operation and returned fields, and the second adds the important search-cost note. No 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?

With no output schema, the description usefully enumerates the profile fields returned and notes the cost. It could mention invalid-ref behavior or partial-result handling, but is otherwise sufficient for this simple read 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 coverage is 0%, so the description must compensate. It does so by explaining that refs are exhibitor references in E1234 format and that up to 5 exhibitors can be requested, aligning with the maxItems constraint.

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?

Clearly states it returns full exhibitor profiles by reference and lists the included fields, so the agent knows the resource and output shape. It does not explicitly distinguish itself from siblings like search_listings or check_fit, keeping it below 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 phrase 'by ref (E1234)' implies usage when exhibitor refs are already known, and 'Spends one search' gives a cost cue. However, it does not explicitly name alternatives or state when not to use this tool.

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?

Annotations already declare readOnlyHint and closed-world, so the description correctly focuses on value-add: it is free, consumes no search quota, and the duty field is conditional ("where known"), warning the agent that output may be partial. It omits what happens with zero matches or how categories are matched.

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 dense sentences: the first front-loads the returned metrics, the second carries the cost and quota caveat. Nothing is redundant or padded.

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 no annotation coverage of returns, the description does the work of naming the returned statistics and the conditional duty field. Currency, units, and minimum sample size for a meaningful band are unaddressed but are secondary for a lookup 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?

The single parameter has 0% schema description coverage, so the description must carry the burden; "for a product" and "matching fair categories" hints that query is a product term matched against categories. It does not specify expected format (SKU vs. keyword), which is a real gap for the only required input.

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 the resource (price statistics for a product) and enumerates the specific outputs: median, middle half, median MOQ, and US import duty. This is clearly distinct from search_listings or get_exhibitors, though it does not name a sibling explicitly.

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?

"Free; does not spend a search" implies this is the cheap alternative to a full listing search, which is real usage signal. However, it never states when to prefer this over search_listings or what happens when no priced listings match, leaving the selection decision partly to inference.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds genuinely new behavior: it costs one search credit, it returns totals plus ranked exhibitors with their listings, and filters scope to the exhibitors returned rather than the listings. That last point is a non-obvious semantic an agent could easily get wrong.

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?

Four short sentences, each carrying distinct information: purpose, return shape, query convention, filter scoping, and search cost. Zero filler and the scope statement is front-loaded.

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?

No output schema exists, yet the description covers the return shape, the search-credit cost, and filter scoping — the main things an agent needs. Minor gaps: 'phase' and 'limit' semantics are not elaborated, and no alternative tool is named, but for a 5-param read-only search this is close to sufficient.

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?

With 60% schema coverage, the description compensates by clarifying that optional filters ('type', 'certificate', presumably 'phase') apply to the exhibitors returned, not to the listing match — a real semantic addition the schema does not state. 'query' is reinforced as product words only, matching the schema; 'limit' is left unexplained but is bounded 1-10 in 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?

States a specific verb and resource ('Search exhibitors' product listings and profiles') plus scope ('across the whole fair'), and the return shape ('totals and best-matching exhibitors with their matching listings'). It is distinguishable from get_exhibitors and check_fit by implication, though 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.

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

Gives concrete usage guidance: 'Use product words only (e.g. bamboo cutting board)' and 'Spends one search', which signals a budget/quota consideration. It does not explicitly say when to prefer get_exhibitors or check_fit instead, so it stops short of full alternative routing.

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?

Annotations already cover readOnlyHint, but the description adds genuinely new behavioral facts: it is free and does not consume a search credit, and it discloses what the response contains (sourced rules plus factory certificates/test reports). It doesn't say anything about coverage limits or staleness of the regulatory data, which is the main remaining unknown for a compliance tool.

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 dense sentence plus a short cost note, front-loaded with the scope. Every clause carries information, though the parenthetical "(Amazon)" and the certificate clause make it slightly run-on.

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?

No output schema exists, so the description must convey what comes back — and it does, naming sources and certificate/test-report artifacts. The one gap is the input format for 'product', which is unspecified in both schema and description.

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?

There is one required parameter, 'product', with 0% schema description coverage, so the description carries the full burden — and it only repeats "product" in prose without saying whether it expects a plain name, a category, an HS code, or a description. An agent has to guess the accepted granularity, which materially affects result quality.

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 pair: what a US seller must check before importing and selling a product. The enumeration of contents (laws, marketplace/Amazon rules, buyer requests) plus deliverables (sources, certificates, test reports) makes it unmistakable against siblings like price_bands or search_listings.

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?

"Before importing and selling a product" gives a clear trigger context, and "does not spend a search" hints at when to prefer this over the search-family siblings. It doesn't explicitly name an alternative or state when not to use it, so it stops short of full routing guidance.

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