Server Quality Checklist

Tool Scores

• get_itemsA
  4/5.0
  Behavior5/5

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

  Annotations declare readOnlyHint and openWorldHint, and the description adds high-value behavioral details: the returned items array is not ordered, invalid ASINs appear in an errors array, format defaults are specified, and HTML-only styling parameters are explained. No contradiction with annotations.

  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 well-structured with a clear first sentence, bolded warnings, and a separate presentation guidance section. It is longer than necessary with some repetition of format guidance, but the key information is front-loaded and scannable.

  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 tool with 10 parameters and no output schema, the description covers critical runtime behavior: array ordering, error handling, output formats, and post-tool presentation. It does not detail merchant/condition/resources, but the schema provides those descriptions. Overall, it is sufficient for correct invocation and result handling.

  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 70%, and the description enriches several parameters: it explains format defaulting and HTML usage, titleMaxChars clamping behavior, hideItemsWithoutPrice default, and the asins ordering caveat. This goes beyond the schema's descriptions for those parameters.

  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?

  The description opens with 'Look up 1–10 ASINs on Amazon', which clearly states the specific verb and resource. However, it does not explicitly differentiate from sibling tools like search_items or get_variations, though the focus on ASINs is implied.

  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?

  Extensive guidance is provided for choosing output formats (markdown/json vs html-card/html-grid) and for post-tool conversational summarization. However, there is no explicit guidance on when to use get_items versus sibling tools like search_items or get_variations; usage is only implied by the phrase 'Look up ... ASINs'.

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

• get_browse_nodesA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and openWorldHint=true, covering safety. The description adds meaningful behavioral context beyond annotations: the output includes 'ancestor chain and direct children for each node', supports 'markdown' and 'json' output, and explicitly excludes 'HTML product-card formats'. It does not address rate limits or pagination, but the bar is lower given strong annotations.

  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 two sentences, front-loaded with the core purpose. The first sentence states the function and scope, the second adds a usage tip and a format constraint. Every sentence earns its place with no redundant filler.

  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 read-only metadata tool with strong annotations, the description is reasonably complete: it explains the return content (ancestor chain, children, up to 10 IDs), mentions resource options via the sales rank tip, and discloses format limitations. It does not detail every parameter (e.g., languagesOfPreference), but that is a minor gap given the tool's simplicity.

  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 75% (three of four parameters have descriptions). The tool description reinforces some parameter semantics ('up to 10 IDs' aligns with browseNodeIds maxItems, and it mentions the supported formats), but it does not explain 'languagesOfPreference', which lacks a schema description. Given the schema still handles most parameter meaning, a 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 tool's function: 'Returns browse-node metadata (category tree) for up to 10 IDs — ancestor chain and direct children for each node.' This uses a specific verb ('Returns') and resource ('browse-node metadata'), and the scope ('up to 10 IDs', 'ancestor chain and direct children') distinguishes it from sibling tools like get_items or search_items, which serve different purposes.

  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 context for when to use the tool, including a specific use case: 'Use the `browseNodeInfo.websiteSalesRank` resource to find top-selling categories.' It also gives a when-not constraint: 'HTML product-card formats don't apply here.' However, it does not explicitly name alternative tools or exclusions relative to siblings, so it misses the highest bar.

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

• search_itemsA
  4.3/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses pagination limits (itemPage 2..10, 100 items max), the totalResultCount caveat, and marketplace currency. It also spells out that HTML formats return a full document only when explicitly requested, and that raw output should not be pasted into chat. No contradiction with annotations.

  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 front-loaded with a one-sentence purpose, then adds concise pagination and currency facts, and closes with an important (clearly labeled) presentation block. The example summary is a bit verbose, but it vividly illustrates the expected chat behavior. No fluff; structure is logical.

  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 25-parameter tool with no output schema, the description covers the essential operational model: search scoping, pagination, result-count caveat, currency, and output-format semantics. It doesn't describe the exact response shape (e.g., where items live in the JSON) or error/empty cases, but the resource parameter and presentation guidance partially cover that. Overall it is complete enough for effective autonomous use.

  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?

  The description groups actor/author/brand/title/browseNodeId as optional search scoping filters, adding meaning beyond their bare schema entries. It also clarifies that minPrice/maxPrice are in cents/pence implicitly via 'prices are in the marketplace's currency'. However, several enum parameters (sortBy, condition, merchant, availability) remain unexplained in both prose and schema, so parameter coverage is only partially enhanced.

  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 opens with 'Search Amazon's catalog by keywords', a specific verb and resource. It lists optional filters (title/actor/author/brand/browse-node) which distinguishes it from sibling tools like get_items that likely retrieve by ID. The purpose is unmistakable.

  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 provides clear context that this tool is for searching the catalog, but it never names sibling tools or says when not to use it. The PRESENTATION GUIDANCE covers output-format choice (markdown/json vs html-card/grid), which is intra-tool usage, not tool-vs-alternative guidance. Thus usage is implied, not explicit.

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

• get_variationsA
  4.6/5.0
  Behavior5/5

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

  While annotations already declare readOnlyHint and openWorldHint, the description adds substantial behavioral detail: max 10 variations per call, pagination via variationPage (1–10), empty results for non-variant products, and explicit instructions to avoid pasting raw output and to ask before using HTML formats. These are critical behaviors not captured by 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.

  Conciseness5/5

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

  The description is well-structured: a terse core statement covering purpose, pagination, and variant requirement, followed by a clearly-labelled PRESENTATION GUIDANCE block. Every sentence earns its place, with no filler or repetition of schema content.

  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 12-parameter tool, the description addresses the most critical usage points: pagination, variant requirement, and output format selection. It leverages rich schema descriptions and readOnly annotations effectively, though it doesn't detail the return payload structure (no output schema), which is partially mitigated by the format guidance.

  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 description coverage is 67%, so the description doesn't need to compensate fully. It enriches key parameters: variationPage (1–10 pagination), format (default to markdown/json, HTML only when explicitly requested), and the notion of a sensible default set for resources. It doesn't describe merchant/condition/languagesOfPreference, but those are self-explanatory via enums and naming.

  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 'List colour/size/style variations of a parent ASIN' — a specific verb and resource that clearly distinguishes it from sibling tools like search_items or get_browse_nodes. It also adds scope details (max 10 per call, pagination, empty result for non-variant products), which further clarifies the tool's exact function.

  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?

  Provides clear context for use (pass parent ASIN of a product with variants) and a clear exclusion (non-variant products return empty result). It does not explicitly name alternative tools, but the purpose is distinct enough that the agent can infer when to choose this tool. The presentation guidance also specifies when to use markdown/json vs HTML formats, which aids correct usage.

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

• format_itemsA
  4.8/5.0
  Behavior5/5

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

  Beyond the readOnlyHint annotation, the description discloses that no API call is made, data must come from a previous call, and that it is a re-rendering operation. This adds meaningful behavioral context (rate-limit avoidance, no external mutation) that complements 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.

  Conciseness5/5

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

  Two sentences with no filler. The first sentence establishes the core purpose and inputs, the second provides concrete usage scenarios and benefits. Well structured and properly front-loaded.

  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?

  While there is no output schema, the rich parameter descriptions (especially the format enum) effectively explain what the tool produces. The description could explicitly say 'returns the formatted output' but this is strongly implied by the verb 're-render' and the format details. Overall it is complete enough for reliable tool selection and invocation.

  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?

  The input schema already has 100% coverage with detailed descriptions for each parameter. The description adds workflow value by clarifying the two alternative input paths (response vs. items) and linking to previous calls, but the schema alone is largely sufficient.

  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 re-renders already-fetched Amazon items without re-hitting the API, using a specific verb ('re-render') and naming the exact prior calls that produce the input. It explicitly contrasts with sibling retrieval tools by emphasizing it is for formatting existing data, not fetching new data.

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

  Usage Guidelines5/5

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

  It explicitly tells when to use the tool: for producing HTML embeds after the user asks for a card/grid/preview, and specifically when iterating on customStyles. It also mentions avoiding rate-limit pressure and being faster than re-querying, giving clear reasons to prefer this over alternatives.

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