Server Quality Checklist

Tool Scores

• get_glucose_statsA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It discloses the calculation nature but doesn't mention any potential caveats, preconditions (e.g., connection), output format, or error handling. The description adds no behavioral context beyond the obvious read-only calculation.

  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 sentences, first is a clear action statement, second adds context. No filler, front-loaded with the verb.

  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?

  The tool has one optional param, no output schema, no annotations. The description lists the metrics computed, but misses any note on output structure or preconditions. It's adequate for a simple stats tool but leaves some gaps.

  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 schema fully describes the days parameter with default and range. The description doesn't mention parameters but that's unnecessary given 100% coverage. 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?

  Description clearly states the tool calculates glucose statistics with specific metrics (average, GMI, TIR, variability). It distinguishes from sibling tools like get_current_glucose (single reading) and get_glucose_history (raw data).

  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 says it's 'essential for diabetes management insights' but doesn't explicitly contrast with sibling tools or state when to use it instead of history/trends. Usage is implied by the nature of the tool, but no direct alternatives are mentioned.

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

• get_glucose_trendsA
  3.8/5.0
  Behavior3/5

  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 explains the analytical purpose and the types of patterns examined, but does not explicitly state whether the operation is read-only, if it requires a connection or historical data, or what the output format is. The 'get' prefix in the name suggests safety, but the description itself does not confirm.

  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 two sentences and front-loaded with the core action. The second sentence, while helpful, is somewhat generic ('Helps identify recurring patterns...') and could be more specific about output or use cases, but it does not contain unnecessary fluff.

  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 absence of an output schema and annotations, the description should explain what the tool returns. It mentions identifying patterns but does not describe the structure of the result (e.g., a report, list, or chart). For a simple tool with one optional parameter, this is a moderate gap, making it only partially complete.

  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 schema description covers 100% of the parameter, providing detailed semantics for the 'period' enum (daily, weekly, monthly) with usage guidance. The main description adds no additional parameter information, so it relies on the schema. The baseline score of 3 applies due to high 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 specifies the tool's action ('Analyze') and resource ('glucose patterns'), naming specific pattern types (dawn phenomenon, meal responses, overnight stability). This distinguishes it from sibling tools like get_glucose_history (raw data) and get_glucose_stats (aggregated statistics).

  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 conveys when to use the tool: 'Helps identify recurring patterns that may need attention or treatment adjustments.' It does not explicitly mention alternatives or exclusions, but the context is clear enough for an agent to select it for pattern analysis over raw history or basic stats.

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

• configure_rangesA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explains the effect on personalized time-in-range calculations and mentions the standard range, but it does not disclose whether the setting persists, whether there is validation (e.g., target_low < target_high), or what happens after the range is set. This is a moderate disclosure but leaves key operational details unstated.

  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 long, with the primary action stated first and supporting context second. There is no fluff or repetition, making it highly concise and 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?

  For a simple two-parameter configuration tool, the description provides purpose, context, and the standard range reference. It lacks details about validation or persistence, but given the simplicity and fully-described schema, the information is mostly sufficient for an agent to select and invoke the tool. A higher score would require more operational detail.

  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 coverage is 100% with detailed descriptions for both target_low and target_high, including common values. The tool description's mention of the standard range (70-180) duplicates what the schema already provides, so it adds no additional parameter semantics. Baseline 3 is appropriate given full 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 the tool's purpose: 'Customize your target glucose range for personalized time-in-range calculations.' It uses a specific verb ('customize') and resource ('target glucose range'), and the phrase 'time-in-range calculations' differentiates it from sibling read/connection tools and configure_credentials.

  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 when to use it: when a healthcare provider recommends different targets than the standard 70-180 mg/dL range. It doesn't explicitly list alternatives or exclusions, but there are no direct sibling tools that compete with this configuration action, making the usage context clear enough.

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

• configure_credentialsA
  4.2/5.0
  Behavior4/5

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

  The description discloses that credentials are stored securely and only on the local machine, a valuable privacy detail not available from annotations. It also hints that the tool can create or update credentials, but doesn't elaborate on validation or error behavior.

  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 compact: two sentences that cover purpose, usage prerequisite, and security. It front-loads the main action and avoids 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 annotations or output schema, the description covers the core essentials: what it does, when to use, and a security property. It lacks details on outcomes or confirmation, but this is acceptable for a simple configuration 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 covers all parameters with 100% description coverage, so the description adds no extra parameter semantics. The baseline of 3 applies since schema does the heavy lifting.

  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 with a specific verb ('Set up or update') and resource ('LibreLink account credentials'), linked to data access. It distinguishes itself from sibling tools that retrieve glucose data, making its purpose unmistakable.

  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?

  It explicitly states that credentials are required before using any glucose reading tools, establishing a clear prerequisite. While it doesn't mention alternatives (there are none for credential setup), the context is strong enough to guide the agent.

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

• get_sensor_infoA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It does indicate the kind of information returned (activation date, remaining lifetime, connection status) and implies a read-only operation, but it does not disclose how the tool behaves if no sensor is active, if connection fails, or whether it requires prior configuration. This is a moderate level of transparency.

  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 concise sentences, front-loaded with the primary purpose and followed by a clear use case. Every word contributes meaning, with no fluff or repetition.

  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 zero-parameter read-only tool, the description covers the essential context: what the tool does, what data it returns, and when to use it. It lacks details about error states or return format, but given the simplicity and the absence of an output schema, the description is adequately 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, so the baseline is 4. The description adds no parameter-specific details, but none are needed. The information about what data is retrieved compensates for the lack of parameters in explaining what the tool does.

  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: to retrieve information about the active FreeStyle Libre sensor, listing specific data points (activation date, remaining lifetime, connection status). The verb 'Get' is specific and the resource is well-defined, and this distinguishes it from sibling tools that focus on glucose data or configuration.

  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 explicit context for when to use the tool: 'Use this to check if sensor is working properly or needs replacement.' This gives clear usage guidance, though it does not explicitly mention alternatives or when not to use it. The sibling tool names imply other tools for glucose-specific tasks, but the description does not cross-reference them.

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

• validate_connectionA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the transparency burden. It discloses that the tool returns a success/failure status and tests connectivity/credentials. However, it does not mention potential error types, latency, or whether any state changes occur, which would be valuable but not critical for a simple test operation.

  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, front-loaded sentences: what it does, when to use it, and what it returns. Every sentence earns its place, with no filler or repetition of schema information.

  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 parameterless, simple diagnostic tool, the description is sufficiently complete: it states the purpose, usage scenario, and return value. Lacking an output schema, the mention of 'success/failure status' is adequate. It could be slightly more detailed about what 'success' means, but this is a minor gap.

  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 the schema coverage is 100% (vacuous). The baseline for zero-parameter tools is 4, and the description does not need to explain parameters. It correctly focuses on the tool's action and return value.

  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 tests the connection to LibreLink servers and verifies credentials. It uses a specific verb ('Test') and resource ('connection to LibreLink servers'), and distinguishes itself from sibling tools by focusing on connection validation rather than data retrieval or configuration.

  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 when to use this tool: 'if you encounter errors or after updating credentials'. It does not explicitly name alternatives, but this usage context is clear and distinguishable from sibling tools like configure_credentials or get_current_glucose.

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

• get_glucose_historyA
  4.3/5.0
  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 of behavioral disclosure. It states the return format ('array of timestamped glucose values') and the default behavior ('Default retrieves 24 hours of data'). This is sufficient for a simple read-only operation, though it does not disclose details like chronological ordering or unit of measure.

  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 succinct sentences, each adding distinct value: purpose, return type, and common use cases with the default behavior. There is no redundancy or fluff, and the most important information is front-loaded.

  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 tool with one optional parameter and no output schema, the description is complete: it explains what the tool does, what it returns, and the default window. It omits minor details like timezone or units, but these are not critical for a basic history retrieval tool given the clarity of 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?

  The schema description covers 100% of parameters with detailed information: range (1-720), default (24), and examples (1, 8, 168). The description adds only a reinforcement of the default, providing no additional semantic value beyond the schema. Baseline 3 is appropriate when schema does the heavy lifting.

  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 retrieves historical glucose readings, using a specific verb ('retrieve') and resource ('historical glucose readings'). This distinguishes it from sibling tools like get_current_glucose, which focuses on current readings, and get_glucose_stats, which provides statistical summaries rather than raw data.

  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 explicit use cases: 'reviewing past glucose levels, identifying patterns, or checking overnight values.' This gives clear context for when to use the tool, but it does not explicitly mention alternatives or exclusion rules, such as 'for current glucose, use get_current_glucose.'

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

• get_current_glucoseA
  4.5/5.0
  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 of behavioral disclosure. It does this well by explaining what the tool returns: current glucose in mg/dL, trend direction, and in-target status. It doesn't discuss side effects or error scenarios, but for a read-only getter, the behavior is transparent and the output is clearly specified.

  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, both valuable. It front-loads the primary action ('Get the most recent glucose reading') and then immediately provides the key return details and the intended use case. There is no redundant or filler content; every clause earns its place.

  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 simplicity (no parameters, no annotations, no output schema), the description is complete. It explains what it returns, the unit of measurement, and the use case. It also positions the tool among siblings by focusing on 'most recent' and 'real-time,' covering all necessary context for an agent to select and invoke it correctly.

  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, so the description is not required to explain parameter semantics. The baseline for zero parameters is 4, and the description appropriately focuses on the output rather than input. No additional parameter clarification is needed.

  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 a specific verb and resource: 'Get the most recent glucose reading from your FreeStyle Libre sensor.' It further distinguishes itself from siblings by focusing on the current reading, not history, stats, or trends. It also enumerates the returned data (value, trend, target range), making the purpose unmistakable.

  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 identifies the use case: 'Use this for real-time glucose monitoring.' This gives clear context for when to use the tool. It doesn't mention alternatives or exclusions, but the real-time focus implicitly differentiates it from historical tools like get_glucose_history or aggregation tools like get_glucose_stats.

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