Server Quality Checklist

Tool Scores

• refresh_sessionA
  3.7/5.0
  Behavior1/5

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

  The description states 'Discard the in-memory login session,' which is a state-changing action, while annotations declare readOnlyHint=true. This is a direct contradiction. Although the description adds helpful non-effect details, the contradiction undermines trust in behavioral 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?

  Two sentences with no filler: the first names the action and its immediate consequence, the second clarifies what it does not affect. The most critical information is front-loaded.

  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?

  For a zero-parameter tool, the description explains purpose, the next-request effect, and non-effects, which is largely complete. However, the annotation contradiction leaves the operation's true semantics ambiguous, so the overall context is not fully reliable.

  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%, so there is no parameter information missing. The description reasonably adds no parameter details because none exist.

  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 ('Discard') and resource ('in-memory login session'), making the action unambiguous. It also differs clearly from the sibling tools, which are all data-retrieval or health-check operations, and adds what the tool does not do.

  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 phrase 'The next data request authenticates again' gives clear context for when the effect occurs, but it does not explicitly state when to prefer this tool over alternatives or provide exclusions. The sibling list makes the niche apparent, so guidance is adequate but not fully explicit.

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

• get_latest_measurementA
  4/5.0
  Behavior4/5

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

  Annotations already mark this as read-only, idempotent, open-world, and non-destructive. The description adds useful non-obvious behaviors: it returns null when no measurement matches and refuses to claim latest if a scan limit is reached. The scan-limit wording is somewhat vague, but it still discloses an important edge case beyond what annotations convey.

  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?

  Three short sentences with no filler. The core purpose is front-loaded, and each subsequent sentence adds distinct behavioral information: null return and scan-limit refusal. Every sentence earns its place.

  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 tool with one optional parameter, strong safety annotations, and no output schema, the description covers the main behavior, the null case, and an important limit-related edge case. The only shortfall is that 'Refuses to claim latest if the scan limit is reached' is ambiguous about what the tool actually returns or does in that scenario.

  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%, and the schema already fully documents the single optional parameter, including its source (get_scale_users) and default behavior when omitted. The description adds no additional parameter-level meaning, so the baseline score of 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?

  The description states a specific action ('Read'), a specific resource ('the latest owned measurement'), and what fields are included ('all available body composition fields'). It clearly distinguishes itself from siblings like get_measurements and get_weight_trend by emphasizing 'latest'.

  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 its use case through the word 'latest', but it does not explicitly say when to prefer this over get_measurements or get_weight_trend, nor does it state any exclusions. The parameter cross-reference to get_scale_users provides some context but not tool-selection guidance.

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

• get_measurementsA
  4.4/5.0
  Behavior5/5

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

  Beyond the annotations, the description discloses meaningful behavior: results are sorted newest-first, ownership filtering occurs before pagination, scanComplete must be checked before treating results as complete, and no health classifications are computed. These are specific, non-obvious traits that materially affect how an agent should interpret the response.

  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?

  Three tightly written sentences, each carrying distinct information: what the tool reads, ordering/format, and crucial interpretation caveats. Nothing is redundant, and the most important action 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?

  For a no-output-schema read tool, the description covers the key operational facts: ordering, raw field format, ownership filtering, completeness checks, and absence of health classifications. It does not enumerate the exact RENPHO fields returned, but the description provides enough context for an agent to call and interpret the tool correctly without an output 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 already documents since, until, and scaleUserId well. The description adds some relevant context by mentioning ownership filtering and pagination, which maps to scaleUserId and limit/offset. However, it does not clarify limit or offset beyond their names and constraints, and the schema coverage is only 60%, so the description only partially compensates for the undocumented parameters.

  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 opens with a specific verb and resource: 'Read body composition history' and immediately clarifies the sort order ('newest first'). It also distinguishes the raw output ('native RENPHO fields and unit codes') from derived interpretations, making the tool's purpose unmistakable against siblings like get_latest_measurement and get_weight_trend.

  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 gives clear context for when this tool applies: retrieving historical body composition data in reverse chronological order. It does not explicitly name alternatives or exclusion conditions, but the 'history' framing plus the caveat about scanComplete gives an agent enough context to choose it over get_latest_measurement or get_weight_trend.

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

• get_scale_usersA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds value by revealing the output semantics: linked scale tables, profile IDs, and the userIds value's role as scaleUserId. It does not contradict annotations, though it omits edge cases like no linked users or authentication requirements.

  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 tight sentences with no filler. The first sentence front-loads the core action and resource, and the second sentence adds a necessary integration hint about the returned userIds value. Every part earns its place.

  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?

  There is no output schema, so the description carries the burden of explaining return values; it does state the output consists of linked scale tables and profile IDs and explains how to use userIds. For a zero-parameter list tool with strong annotations, this is sufficient, though it could note behavior when no linked tables exist or explicitly reference sibling tools.

  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 has zero parameters, so there is no parameter documentation burden on the description. The schema description coverage is trivially 100%, and the 0-parameter baseline of 4 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?

  The description uses the specific verb 'List' and identifies the resource as 'linked scale tables and profile IDs,' clearly stating the tool's function. It inherently distinguishes itself from sibling tools like get_measurements or get_current_user by focusing on scale user/family profile linkage. No ambiguity remains about what this tool returns.

  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 downstream usage guidance: use the returned userIds value as scaleUserId when selecting a family profile. It does not explicitly compare this tool against alternatives or state when not to use it, but the context of selecting a family profile is sufficient for an agent to select this tool over unrelated siblings.

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

• health_checkA
  4.4/5.0
  Behavior4/5

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

  The description adds behavioral context beyond the readOnly and idempotent annotations by stating what the tool checks (login and scale discovery) and what it does not return (measurements). This helps the agent predict the tool's effect and output scope, though it does not mention whether an error is raised on failed verification.

  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 sentence with no filler. It front-loads the action and resource, then adds the key exclusion about measurements. Every word contributes meaning.

  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, non-destructive health-check tool, the description is largely sufficient. It explains the purpose and the absence of measurement returns, but it does not specify what the tool actually returns (e.g., boolean, status message). Given the simplicity of the tool, 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 no parameters, and the schema fully documents this by defining an empty properties object. The description reinforces that no input is needed, which satisfies the baseline for zero-parameter tools.

  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 the specific verb 'Verify' and names the resource: RENPHO login and scale discovery. It explicitly states that measurements are not returned, which distinguishes it clearly from the measurement-focused sibling 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 intended use case is clear: verify connectivity and authentication setup before taking measurements. Although it does not explicitly name alternatives or state when not to use it, the 'without returning measurements' qualifier strongly implies this is a preflight check rather than a data retrieval tool.

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

• get_current_userA
  4.5/5.0
  Behavior4/5

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

  Annotations already mark readOnlyHint, idempotentHint, and destructiveHint=false. The description adds useful context beyond annotations by stating credentials and tokens are excluded from the profile, which informs agents about data scope. No contradiction.

  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 short sentences, front-loaded with the action and resource. The exclusion note earns its place by adding data-scope clarity without fluff.

  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 zero-parameter, read-only tool with annotations covering safety and idempotence, the description covers what it returns (profile) and what it excludes (credentials/tokens). No output schema exists, but the tool's simplicity means the agent can call it safely and inspect the result. Complete enough.

  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?

  Tool has zero parameters and schema description coverage is 100%. Description adds no parameter details because none are needed; baseline for zero parameters is 4.

  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 states specific verb 'Read' and resource 'logged-in RENPHO Health account profile', and clarifies that credentials/tokens are excluded. This clearly distinguishes it from siblings like get_scale_users (different resource) and refresh_session (session/token operation).

  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?

  Provides clear context for when to use: retrieving the current logged-in account profile. It does not explicitly name alternatives or state when not to use it, but the exclusion of credentials/tokens signals it is not for auth-sensitive data. Clear context without explicit exclusions.

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

• get_weight_trendA
  4.6/5.0
  Behavior5/5

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

  Annotations already mark it read-only and idempotent; the description adds meaningful behavioral detail beyond that: it only considers positive readings, rejects incomplete scans, and rejects inconsistent/missing/mixed unit codes. These details materially affect expectations.

  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?

  Three short sentences, front-loaded with the core purpose. The rejection behavior and disclaimer each add necessary context 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 is sufficient for a simple read-only summary tool with rich annotations. The main gap is that no output schema exists and the description does not specify the exact shape of the summary, though 'Summarize' and the tool name give reasonable grounding.

  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 schema describes scaleUserId well and the description maps 'N days' to the days parameter. The description also adds unit semantics (native kg/lb/stone) that are not present in the schema. It does not deeply elaborate on days, but the name and bounds make it clear.

  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 states a specific verb ('Summarize'), a specific resource ('positive weight readings over the past N days'), and supported units ('kg, lb, or stone'). It is clearly distinct from raw-data siblings like get_measurements and get_latest_measurement.

  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 purpose is stated explicitly enough that an agent knows this is for weight summaries/trends rather than raw measurements. It does not name alternative tools, but the 'This is arithmetic, not medical advice' caveat clarifies a non-usage boundary.

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