Server Quality Checklist

Tool Scores

• list-session-recordingsB
  3.2/5.0
  Behavior3/5

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

  Annotations indicate readOnlyHint=true, destructiveHint=false, and openWorldHint=false, covering safety and scope. The description adds that the tool lists recordings 'based on specified filters' and notes the date filter requirement and format, providing some operational context. However, it doesn't disclose behavioral traits like rate limits, authentication needs, pagination, or error handling, which are relevant for a list operation with complex filtering.

  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 concise and front-loaded, stating the core purpose in the first sentence. The second sentence elaborates on filter examples, and the third specifies the date filter requirement. Each sentence adds value without redundancy, making it efficient for an agent to parse. A slight improvement could be integrating the date filter note more seamlessly.

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

  Completeness3/5

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

  Given the tool's complexity (3 parameters with nested objects, no output schema) and rich annotations, the description is adequate but incomplete. It covers the basic operation and filter scope but lacks details on output format, pagination, error cases, or integration with siblings. For a list tool with extensive filtering, more contextual guidance would enhance completeness.

  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 schema fully documents all parameters. The description mentions filters 'such as URLs, device types, browser, OS, country, city, and more' and specifies that the date filter is required in UTC ISO 8601 format, adding minimal context beyond the schema. This meets the baseline for high schema coverage but doesn't provide significant additional semantic value.

  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 clearly states the tool's purpose: 'List Microsoft Clarity session recordings based on specified filters.' It includes a specific verb ('List'), resource ('Microsoft Clarity session recordings'), and scope ('based on specified filters'). However, it doesn't explicitly distinguish this tool from its siblings (query-analytics-dashboard, query-documentation-resources), which might have overlapping functionality in the same domain.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus its siblings or alternatives. It mentions that 'The date filter is required,' which is a prerequisite, but offers no context about appropriate use cases, exclusions, or comparisons with other tools in the server. This leaves the agent without clear direction on tool selection.

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

• query-analytics-dashboardA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the agent knows this is a safe, read-only operation with limited scope. The description adds useful context about query constraints (single-task focus, time range importance) and the fallback behavior ('prompt the user to specify one'), which goes beyond annotations. However, it doesn't describe rate limits, authentication needs, or response format details.

  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 appropriately sized with four sentences that each add value: purpose statement, query constraints, time range guidance, and fallback behavior. It's front-loaded with the core functionality. Some minor redundancy with the schema description exists, but overall it's efficient.

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

  Completeness3/5

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

  Given the single parameter with 100% schema coverage and annotations covering safety/scope, the description adds reasonable context about query constraints and user prompting. However, with no output schema, the description doesn't explain what data format or structure is returned, which is a gap for an analytics tool. The description is adequate but not comprehensive for this complexity level.

  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% with one parameter 'query' fully documented in the schema. The description reinforces the same constraints (natural language, specific, include time ranges) but doesn't add significant new semantic information beyond what's already in the schema. The baseline of 3 is appropriate when the schema does the heavy lifting.

  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 clearly states the verb 'fetch' and resource 'Microsoft Clarity analytics data' with the mechanism 'simplified natural language search query'. It distinguishes from sibling tools like 'list-session-recordings' by focusing on analytics data retrieval rather than recordings or documentation. However, it doesn't explicitly contrast with 'query-documentation-resources' beyond the analytics focus.

  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 this tool: for 'one specific data retrieval or aggregation task' with 'time ranges explicitly specified'. It warns against 'complex multi-purpose queries'. While it doesn't explicitly name sibling alternatives, it implies this is for analytics queries rather than documentation or recordings. No explicit exclusions are provided.

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

• query-documentation-resourcesA
  3.9/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, covering safety and scope. The description adds useful context about the types of documentation retrieved (snippets, screenshots, guides) and query constraints (focused, single-topic), which helps the agent understand behavioral traits beyond annotations. However, it does not disclose aspects like rate limits, authentication needs, or response format details.

  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 appropriately sized and front-loaded, starting with the core purpose and followed by specific guidelines. Every sentence adds value (e.g., content types, query focus, avoidance of complexity). It could be slightly more concise by combining some clauses, but overall it's efficient with minimal waste.

  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 the tool's moderate complexity (single parameter, no output schema), the description is reasonably complete. It covers purpose, usage, and behavioral context adequately, though it lacks details on output format or error handling. With annotations providing safety and scope info, and schema covering parameters, the description fills most gaps, but could benefit from mentioning response structure or limitations.

  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%, with the parameter 'query' fully documented in the schema. The description adds some semantic context by specifying that queries should be 'focused on one specific documentation topic or question' and 'avoid complex multi-purpose queries', which clarifies intent beyond the schema's technical details. However, it does not provide additional syntax or format guidance, so baseline 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 purpose with specific verbs ('retrieve documentation snippets') and resources ('Microsoft Clarity documentation'), distinguishing it from sibling tools like 'query-analytics-dashboard' which handles analytics data rather than documentation. It specifies the content types (step-by-step screenshots, setup guides, features, etc.) and scope (one specific topic/question).

  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 on when to use this tool ('for finding answers to user questions') and includes explicit usage guidance ('query should be focused on one specific documentation topic or question', 'avoid complex multi-purpose queries'). However, it does not explicitly mention when NOT to use it or name specific alternatives among siblings, though the distinction from 'query-analytics-dashboard' is implied by the content focus.

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