Server Quality Checklist

Tool Scores

• list_profilesA
  4.6/5.0
  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. It discloses the return format and the purpose of each field, which is adequate for a read-only listing tool. It does not mention side effects or prerequisites, but none are expected.

  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: the first states the action, the second details the output and provides usage guidance. Every sentence is useful and there is no 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 zero parameters and presence of an output schema, the description fully explains the return values and connects to the sibling tool. It is complete for a simple listing tool with no additional complexity.

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

  Parameters5/5

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

  There are no parameters, and the description adds value by explaining the output field semantics and linking to sibling tool usage, which exceeds the baseline expectation for a parameter-less tool.

  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 lists Microsoft Edge browsing profiles, with specific mention of returning name, directory, and default status. It distinguishes itself from the sibling tool get_history by showing how its output feeds into that tool.

  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 instructs using the returned values as arguments to get_history, providing clear context for when to use this tool (before retrieving history). It does not mention exclusions, but the guidance is sufficient for this simple listing tool.

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

• get_historyA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavioral traits: pagination with limit/offset, ordering by visit time ascending, timezone interpretation, exclusive end_time, limit cap, and fallback behavior for non-positive values. It also details the return structure including has_more and next_offset. This goes well beyond a simple read-only indication.

  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 and appropriately sized. It opens with a concise summary sentence, then explains pagination and time window narrowing, followed by parameter definitions and return values. Every sentence adds necessary information without redundancy. The formatting with sections (Args, Returns) improves readability.

  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?

  The tool is complex with 6 parameters and pagination, and there is no output schema. The description covers all aspects: parameter semantics, return fields, ordering, paging behavior, and the relationship to list_profiles. It leaves no significant gaps for an agent to select and invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description compensates by explaining every parameter in detail: profile (source from list_profiles), date (format and timezone), start_time/end_time (optional, exclusive bound, default and constraint), limit (default, cap, fallback), and offset (paging). This gives the agent complete understanding beyond the bare 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 verb 'Get', the resource 'Edge browsing history', and the scope 'for a profile on a specific day'. This distinguishes it from sibling tools like list_profiles (which lists profiles) and get_history_summary (which likely provides summaries). The first sentence is specific and unambiguous.

  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: it is for fetching detailed history for a day, can be narrowed to a time window, and is paginated. It references list_profiles as a source for profile names, implying a prerequisite. However, it does not explicitly state when to use this tool versus get_history_summary or mention any exclusions, so it lacks explicit alternative guidance.

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

• get_history_summaryA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden. It discloses critical behaviors: non-web URL filtering, domain normalization, title sampling limits, pagination semantics, and that full URLs are never exposed to protect secrets. This goes far beyond minimal disclosure.

  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 long but well-structured with Args and Returns sections. It is front-loaded with a succinct summary, then detailed parameter and return info. Each sentence conveys necessary information without redundancy, appropriate for a complex tool.

  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?

  There is no output schema, so the description fully explains the return value structure, including nested bucket fields, ordering, and paging metadata. It also covers edge cases like timezone interpretation and limits, making the tool complete and understandable.

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

  Parameters5/5

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

  The schema provides no descriptions (0% coverage), so the description must compensate. Every parameter is explained in detail: formats, defaults, constraints, and behaviors (e.g., end_time exclusive, limit caps, non-positive fallback). This fully covers parameter semantics.

  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 first sentence clearly states the verb and resource: 'Summarize Edge browsing history for a profile on a day, by domain only.' It immediately distinguishes itself from get_history by explaining the aggregation level and security rationale, making its purpose unambiguous.

  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?

  Explicit guidance is given: 'Prefer this tool over get_history for questions like...' and 'Only use get_history when specific URLs are genuinely required.' This directly addresses when to use this tool versus the sibling, satisfying the dimension completely.

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