Server Quality Checklist

Tool Scores

• get_glucose_historyA
  3.8/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the full burden. It reveals one behavioral trait—'ordered oldest-first'—which is useful, but it does not explicitly state that the operation is read-only, mention data units, timezone handling, or error conditions. It is adequate but not rich.

  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 exactly two sentences with no wasted words. The primary action and a key return characteristic are front-loaded, making it easy to scan.

  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 read tool with two fully documented parameters and no output schema, the description adequately covers the purpose and return ordering. The absence of explicit units or timezone is a minor gap, but the tool is still usable for basic historical fetch scenarios.

  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 provides complete descriptions for both parameters (hours range/default and patient_id source), so the schema does the heavy lifting. The tool description adds no parameter-specific information, which matches the baseline score of 3 for 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 states 'Fetch historical blood glucose readings for a patient,' which specifies the verb (fetch), resource (blood glucose readings), and scope (historical, for a patient). It also adds a distinctive detail about the return format ('time-series... oldest-first') that differentiates it from siblings like get_current_glucose and get_glucose_summary.

  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 implies it is for retrieving past glucose data, but it does not explicitly mention when to use it versus alternatives such as get_current_glucose or get_glucose_summary. No exclusions or prerequisites are stated, so the guidance is implicit rather than directive.

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

• get_glucose_summaryA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It communicates the 24-hour window and the output metrics, which are useful, but it does not explicitly state that it is read-only or mention any permissions or side effect expectations. Non-destructive nature is implied but not stated.

  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, front-loaded sentence that efficiently lists the key output metrics and the time span. Every word contributes, with no filler or repetition.

  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 simple (3 optional parameters, no output schema), and the description fully explains the purpose, time window, and the expected return values (the listed metrics). This is sufficient for an agent to invoke the tool correctly.

  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 high detail (patient_id, low_threshold, high_threshold, including defaults). The description adds no parameter-specific context beyond what the schema already provides, so the baseline score of 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 explicitly states the tool summarizes glucose trends over the past 24 hours, listing specific metrics (time-in-range, average, highs, lows, standard deviation). This clearly distinguishes it from siblings 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 implies the tool is for obtaining an aggregate summary rather than raw data, but it does not explicitly mention when to use it vs alternatives. No direct exclusions or alternative tool references are given, so it relies on implicit inference.

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

• get_current_glucoseA
  4/5.0
  Behavior3/5

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

  There are no annotations provided, so the description carries the burden. It discloses what is returned (mg/dL, mmol/L, trend direction), which is useful, but does not mention whether the operation is read-only, data freshness, authentication requirements, or potential errors. For a simple fetch this is acceptable, but it could be richer.

  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 core purpose and key return details, with no wasted words.

  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 simplicity (one parameter, no output schema), the description adequately covers what it does and what it returns. It is slightly limited by not mentioning data freshness or edge cases, but overall it is complete enough for selecting and invoking the 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 schema already provides complete documentation for the single parameter (patient_id from get_connections or leave blank). The description adds no additional meaning about parameters, so it meets the baseline without exceeding it.

  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 action ('Fetch') and the resource ('latest blood glucose reading'), and distinguishes it from sibling tools like glucose history and summary by specifying it returns the current reading with value and trend direction.

  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 context is clear: use this tool to get the most recent glucose reading. However, it does not explicitly compare with alternatives like get_glucose_history or get_glucose_summary, so it lacks explicit when-to-use vs. when-not-to-use guidance.

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

• get_connectionsA
  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 behavioral disclosure burden. It reveals the scope ('associated with the logged-in account') and that the return value contains patient IDs, which implies a read-only list operation. However, it does not explicitly state read-only behavior, error cases, or pagination, leaving some gaps for an agent.

  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, with the main purpose stated first and the return value second. No filler or redundant information is present.

  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 list tool with no output schema, the description provides the essential workflow context (returns patient IDs for glucose tools) and scope. It could add more detail about the exact response structure, but the description is largely complete for its simplicity.

  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?

  There are no parameters to document; the schema is empty with 100% coverage. Per the rubric, the baseline for zero-parameter tools is 4, and the description sensibly adds context about the logged-in account rather than parameter details.

  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 a specific verb 'List' with a clear resource 'patient connections' and scopes it to 'the logged-in account'. It additionally distinguishes from the sibling glucose reading tools by explaining it returns patient IDs needed for those tools.

  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 states the output is 'patient IDs needed for glucose reading tools', which positions this as a prerequisite step before using get_current_glucose, get_glucose_history, or get_glucose_summary. It does not explicitly name alternatives or exclusions, but the workflow context is clear.

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