Server Quality Checklist

Tool Scores

• search_productsA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden. It discloses the paid cost ($0.01), the sampling limitation ('of what we sampled'), the need to read `data_as_of` / `sources` for freshness, and unit normalization (BRL integer cents). These go well beyond generic search behavior.

  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 compact and front-loaded: the first sentence states the core capability, followed by output format details and key caveats. It is dense but each sentence earns its place, with no filler or redundancy.

  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?

  Given 7 parameters and no output schema, the description compensates by enumerating return fields (price, link, imageUrl, shipping flag, rating, seller info) and warning about data freshness and paid cost. It covers the essential context without needing to explain every parameter, since the schema does that.

  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%, and the description adds no parameter-specific meaning beyond what is already in the schema. The output-focused details (e.g., integer cents) do not clarify parameter semantics. Baseline 3 applies.

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

  Purpose5/5

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

  The description states a specific verb ('Search') with a precise resource ('Mercado Livre, Shopee and AliExpress') and clear scope ('in ONE call'). It differentiates from siblings like search_by_image and calculate_import_taxes by emphasizing multi-marketplace search and normalized offer output.

  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 implies usage as the primary combined search tool, but it does not explicitly state when to use it versus alternatives. It provides contextual cautions (e.g., 'a short list may mean a marketplace was down') but no direct exclusions or comparisons with sibling tools.

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

• search_by_imageA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does well: it discloses the cost ('Paid ($0.05)'), the reliance on a vision model, the possibility of misreading ('if the model misread the photo'), and the behavior of returning interpreted_query. It could add more about failure modes or rate limits, but the disclosed traits are substantive.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences, front-loads the core purpose in the first sentence, and every sentence adds value: what the tool does, how the output relates to search_products, a caveat about interpreted_query, and pricing. There is zero wasted text.

  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?

  The tool is moderately complex (vision model, paid, merged marketplaces) and has no output schema, so the description compensates by clarifying the return value (same as search_products plus interpreted_query) and the potential misread pitfall. It doesn't explain error handling or all return fields, but it is sufficient for a competent agent given the schema.

  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 the description does not need to repeat parameter details. It adds some semantic context by explaining that the vision model reads 'brand, model and attributes' and the query runs across all marketplaces, but no parameter-specific guidance is given. The baseline of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the specific action ('Search from a product PHOTO') and the resource ('Brazilian marketplaces'), and distinguishes it from siblings by noting it returns 'the same normalized offers as search_products, plus interpreted_query'. This makes the tool's unique purpose obvious.

  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?

  The description implies the tool should be used when the user has a product photo, and it contrasts with search_products by noting the photo-based input and the added interpreted_query field. It does not explicitly state when not to use it or name an alternative, but the context is clear enough for an agent to select it appropriately.

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

• search_products_previewA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It clearly states the tool returns one result, provides only a canonical link, excludes affiliate links, and requires no payment. This is useful context, though edge cases and error behavior are not covered.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three short sentences, front-loaded with 'FREE teaser,' and every sentence adds value: cost, output limitation, and use case. There is no filler or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple one-parameter preview tool with no output schema, the description is complete. It covers purpose, usage timing, output constraints, cost, and implicitly contrasts with the paid sibling tool.

  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?

  The input schema fully documents the single parameter q with a description ('What to search for') and minLength. The description adds no parameter-specific meaning, so the baseline of 3 applies due to 100% schema coverage.

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

  Purpose5/5

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

  The description clearly states it is a 'FREE teaser' that previews a product search, with the specific verb 'Preview' and resource 'product search.' It distinguishes itself from the sibling search_products by specifying one result and canonical link only.

  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?

  The description explicitly says 'Use it to check that a query returns something before paying for the full page,' giving clear context for when to use it. It implies the alternative (full paid search) but does not explicitly name sibling tools or state when not to use it.

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

• calculate_import_taxesA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description bears the full burden of behavioral disclosure. It transparently states that the tool is free and deterministic, explains the calculation rule (0% up to US$50, else 30% − US$20), notes the ruleset version and potential changes, clarifies it's an estimate with the marketplace as source of truth, and explicitly says 'No payment.' This goes beyond typical descriptions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and efficiently structured. It front-loads key attributes ('FREE, deterministic'), then explains inputs, outputs, and caveats in a few sentences. Every sentence adds essential information without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (7 parameters, no output schema, no annotations), the description is remarkably complete. It specifies the return values (Import Tax, ICMS, total landed price, USD rate, ruleset version), the input alternatives, the legal basis, and the estimate's limitations. This fully compensates for the lack of structured metadata.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so baseline is 3. The description adds meaningful context by clarifying the exclusive grouping of BRL cents vs USD fields and specifically names product_cents/freight_cents and product_usd/freight_usd, complementing the schema descriptions. It also highlights the optional 'uf' state. This adds value beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool's function: it estimates Brazilian import tax and final landed price for cross-border purchases. The verb 'estimates' is specific, and the resource (import tax/landed price) is clearly identified, distinguishing it from the sibling search tools.

  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?

  The description provides clear usage context: it explains when to use the tool (for estimating import tax/landed price), how to provide inputs (BRL cents or USD, not both, optional state), and what outputs to expect. It does not explicitly mention alternatives because none are relevant (siblings are search tools), but it gives no misleading exclusions.

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