Server Quality Checklist

Tool Scores

• get_conversionsA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, covering the safety profile. The description adds the functional behavior of page-level breakdown, but does not disclose any additional behavioral traits such as rate limits, data freshness, or pagination. Since annotations cover the core safety aspects, a 3 is appropriate.

  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 no redundant content. The primary purpose is stated first, followed by a single distinguishing capability. Every word 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?

  Given the existence of an output schema (not shown) that presumably describes return values, the description does not need to explain response format. The description covers the core functionality and the key optional breakdown feature. For a tool with 6 parameters but only 2 required, this is sufficient; the schema fills in the parameter details, and the annotations cover safety.

  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 all parameters including 'breakdown_by_page', 'goal', and 'page' are documented in the schema. The description's mention of 'can break down by page' adds a slight contextual hint but largely repeats what the schema already provides. Thus, the added value over the schema is minimal, warranting the baseline 3.

  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 ('Get') and resource ('goal conversion rates and counts'), and adds the distinguishing capability 'Can break down by page to see which pages drive conversions.' This clearly separates it from sibling tools like get_timeseries or get_breakdown, which focus on different aggregations or dimensions.

  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 explicit guidance on when to use this tool versus the sibling tools (get_timeseries, get_breakdown, compare_periods). It does not mention alternatives or exclude specific use cases, leaving the agent to infer usage from the schema and context.

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

• compare_periodsA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered structurally. The description adds useful behavioral context by specifying the return semantics ('aggregate values for each period plus the delta (absolute and %)'). It does not contradict the annotations, but it omits nuances like metric defaulting or how filters are combined, which the schema covers.

  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 zero filler. The core purpose is front-loaded, the use case follows, and the return format closes it. Every sentence earns its place.

  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 7-parameter tool with 100% schema coverage, an output schema, and rich annotations, the description adequately conveys the essential scope, use case, and return format. However, it does not mention the optional filter (property_filters) or metric defaulting behavior, leaving the agent dependent on the schema for those details — reasonable, but slightly short of fully self-sufficient.

  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 baseline is 3. The description reinforces the core parameters by mentioning 'two date ranges' (period_a/period_b) and 'metrics', and maps naturally to those fields. It adds little beyond the schema, which is acceptable given the schema's completeness.

  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 ('Compare'), a specific resource ('metrics between two date ranges'), and the side-by-side comparison framing that distinguishes it from siblings (get_timeseries, get_breakdown, get_conversions). It also names the return shape (aggregate values plus delta), so an agent can identify this tool without opening the schema.

  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 gives an explicit use case ('Ideal for before/after deploy analysis') that helps an agent decide when to invoke it. However, it does not name the sibling tools or state when NOT to use it (e.g., for time-series trends or single-period breakdowns), leaving the differentiation to inference from tool names rather than explicit routing guidance.

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

• get_breakdownA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, covering the safety and repeatability profile. The description adds no behavioral details (e.g., pagination, limits, or mutation effects). Since annotations cover safety, the bar is lower, but the description contributes no extra behavioral context beyond the generic 'break down' phrasing.

  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 zero waste. The core action is front-loaded ('Break down metrics by a dimension'), followed by a practical usage note. Every element earns its place; no redundancy or filler.

  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?

  Despite having 7 parameters, all are described in the schema, and an output schema exists (as per context signals). The description provides enough context for an agent to know when to call this tool, relying on the schema for parameter details and the output schema for return structure. It could mention limits or filters, but those are already in the schema. The description is adequate for this complexity.

  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 all 7 parameters have detailed descriptions in the schema. The tool description mentions 'dimension' generically and the purpose, but doesn't add any parameter-specific information beyond the schema. With high schema coverage, the baseline of 3 applies.

  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 and resource: 'Break down metrics by a dimension' and lists example dimensions (page, source, country). It conveys the purpose without tautology. While it doesn't explicitly differentiate from siblings like get_timeseries or get_conversions, the concept of dimension-based grouping is distinct enough for an agent to infer usage.

  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 usage context: 'Use to find top pages, sources, or segment traffic.' It tells the agent when to apply the tool, but doesn't explicitly state when not to use it or name alternative tools. This matches the 'clear context, no exclusions' tier.

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

• get_timeseriesA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, covering the tool's safety and repeatability. The description adds the scope of 'for a site or specific page' and the purpose of spotting trends, which is contextually useful but does not disclose additional behavioral details like aggregation behavior, output formatting, or rate limits. Since annotations cover the core profile, a neutral score of 3 is appropriate.

  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 followed by a specific intended use case. There is zero waste; each sentence earns its place. It is concise and well-structured.

  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 (7 parameters) but fully documented schema and an output schema (indicated by context signals), the description is sufficient. It clearly states what the tool returns (metrics over time) and a typical use case. No critical missing information prevents an agent from invoking it correctly, though it could mention that it can be filtered by page or custom properties, but that is already in the schema. Overall, it is complete enough for this read‑only analytics 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?

  Schema description coverage is 100% — every parameter (site_id, date_range, goals, page, metrics, granularity, property_filters) is described in the input schema with types, defaults, and examples. The description adds no extra parameter information, so it does not exceed the baseline of 3. It neither clarifies nor complicates the parameters.

  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 function: 'Get traffic and conversion metrics over time for a site or specific page.' It identifies the resource (metrics) and the temporal context, making its purpose unambiguous. However, it does not explicitly distinguish itself from sibling tools like get_breakdown or compare_periods, though the 'over time' phrasing implies a time-series focus. This is clear but not fully differentiated from alternatives.

  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 concrete use case: 'Use to spot trends and changes around deploys.' This gives clear context for when the tool is appropriate. It does not, however, mention when not to use it or point to alternative tools for other scenarios, so it lacks explicit exclusions that would earn a 5.

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