Server Quality Checklist

Tool Scores

• list_paired_devicesA
  4.2/5.0
  Behavior3/5

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

  Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds context about the returned information (manufacturer/model/type) but does not disclose additional behavioral traits like rate limits or authentication needs, which are not critical given 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 a single, efficient sentence that conveys the purpose and a use case without any unnecessary words. It is well-structured and front-loaded with the action.

  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 has no parameters and no output schema, the description adequately covers the functionality and a typical use case. It could mention if there are limits on the number of devices returned, but for a simple list tool, it is sufficiently complete.

  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 tool has zero parameters, and schema description coverage is 100%. The description adds value by specifying what information the list includes (manufacturer/model/type) beyond what the schema provides, making it more useful.

  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 lists devices paired to the Google Health account, with specific examples (Apple Watch, Fitbit Air, Pixel Watch) and details on what information is included (manufacturer/model/type). This is distinct from sibling tools like connection_status or list_data_points.

  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 a clear use case: 'Useful to confirm a new device has connected.' This informs when to use the tool, though it does not explicitly mention when not to use it or compare with alternatives.

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

• connection_statusA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the description rightly focuses on additional behavioral details: checking token validity, scope alignment, and data return over 7 days. No contradictions.

  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 cover both technical behavior and usage guidance. No wasted words; information is 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?

  Given no output schema, the description adequately describes the return value (token status, scopes, metric availability). Could include more structured output hints, but sufficient for decision-making.

  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?

  With zero parameters, the instruction allows a baseline of 4. The description adds value by explaining what the tool does without relying on parameter documentation.

  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 uses specific verbs ('health-check', 'confirms', 'reports', 'probes') and identifies the exact resource ('Google Health connection'). It clearly distinguishes from siblings like get_daily_summary or list_data_points, which have 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?

  Explicitly states when to run this tool: 'first when setting up or after a new device syncs'. It doesn't mention when not to use it, but the context is clear and actionable.

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

• get_daily_summaryA
  4.6/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about data aggregation across sources and return format, but does not mention any potential performance or state implications.

  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 (4-5 sentences), front-loaded with what the tool returns, and efficiently covers parameter usage without 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 no output schema, the description mentions return structure (per-day table plus raw points) and covers parameter combos. Lacks minor details like output format specifics or constraints.

  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 guidance on parameter relationships (start_date vs. days) and usage examples, which goes beyond raw schema descriptions.

  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 returns daily health metrics across all connected sources, and distinguishes itself from siblings like sync_health_to_obsidian by being the primary trend tool.

  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?

  Explicitly guides when to use start_date/end_date vs. days, how to subset metrics, and positions itself as the primary tool for trend questions, implicitly differentiating from sibling tools.

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

• list_data_pointsA
  4.6/5.0
  Behavior4/5

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

  Description adds behavioral context beyond annotations: confirms read-only nature, explains pagination defaults (most recent first, max pages/ page size limits), and notes raw filter complexity. No contradictions 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.

  Conciseness5/5

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

  Two concise paragraphs with no redundant sentences. Every sentence adds distinct information: purpose, use cases, parameter behavior, and alternative. Well-structured for quick reading.

  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?

  Covers all necessary aspects given tool complexity: purpose, parameters, usage guidelines, and behavioral quirks. No output schema exists, so return value details are omitted, but context is sufficient for correct 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?

  Schema descriptions already cover all 4 parameters with 100% coverage. Description adds value by mapping common keys to raw dataType strings and clarifying the filter parameter's obscurity, enhancing usability.

  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 fetches raw health data points with finer-than-daily granularity, distinguishing from get_daily_summary by mentioning intraday data and dataType coverage. The verb 'fetch' and specific resource (raw data points for a single Google Health dataType) are precise.

  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?

  Explicitly states when to use (finer granularity, unsupported dataTypes) and when to use alternative (get_daily_summary for trends). Provides clear guidance with comparative cost hint ('far cheaper'), aiding selection.

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

• sync_health_to_obsidianA
  4.6/5.0
  Behavior5/5

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

  The description discloses that the tool writes to files (export/refresh), specifies the output paths and frontmatter fields, explains incremental vs full sync behavior, and notes the requirement of OBSIDIAN_VAULT_PATH. This adds significant value beyond the annotations, which only indicate not read-only and not destructive.

  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 primary action, and efficiently covers the mechanism, optional full sync, and prerequisites. Every sentence provides essential information without 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?

  The description covers the tool's purpose, behavior, and parameters well. However, it does not mention the return value or behavior on error, which could be useful since no output schema is provided. Overall, it is mostly complete for usage.

  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 descriptions for all 4 parameters. The description adds context by explaining the default behavior of incremental sync and the role of full_sync, and implies the relationship between days and start_date. This adds marginal 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 exports daily health summaries to Obsidian as per-day markdown notes and refreshes a dashboard. It uses specific verbs (export, refresh) and resources (per-day notes, dashboard), and distinguishes from sibling tools that focus on data retrieval or connection status.

  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 explains the default incremental behavior and how to trigger a full sync, and mentions the required environment variable. It provides clear context for usage but does not explicitly state when to avoid this tool or compare it to alternatives, though the context from sibling tools makes it distinct.

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