Server Quality Checklist

Tool Scores

• get_growthA
  4.6/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, but the description adds meaningful behavioral detail beyond these: values are on a 0-100 scale, absolute volume is included when available, windows are preset strings, and rate-limit/quota failures should be reported as a plan limit reached. No contradiction 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.

  Conciseness4/5

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

  The core purpose is front-loaded in the first sentence, followed by output-scale details, sibling preference, source clarification, and error handling. It is slightly long and some points duplicate schema content, but every sentence earns its place by clarifying usage or behavior.

  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?

  With an output schema present, the description does not need to explain return structure. It covers what the tool does, when to choose it over siblings, source constraints, output scaling, and the rate-limit failure mode. Nothing needed to invoke it correctly is missing.

  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 already provides rich documentation: source lists valid values and comma-separated behavior, keyword specifies per-source formats, and percent_growth enumerates all preset windows. The description reinforces the preset-window idea and Android bundle ID requirement but adds little genuinely new parameter information beyond what the schema already covers.

  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: 'Point-to-point growth for a keyword on one or more sources.' It also explicitly distinguishes itself from siblings by saying to prefer it over get_time_series for growth questions and clarifying that app sources are not the live boards on get_top_trends. This makes the tool's unique purpose immediately clear.

  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?

  The description gives direct guidance: 'Prefer this over get_time_series for growth questions' and clarifies that app downloads/app rankings sources are not the App Store/Google Play live boards on get_top_trends. It also tells the agent what to do on rate limiting or quota exhaustion, which is practical usage guidance.

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

• get_time_seriesA
  4.7/5.0
  Behavior5/5

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

  The description adds meaningful behavioral details beyond the readOnly/openWorld/idempotent annotations: the series is limited to 0-100 values, volume is included 'when available,' and there is a clear instruction on how to handle rate limits or quota exhaustion. No contradiction 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?

  Three concise sentences, each earning its place: the first defines output, the second gives usage context and alternatives, and the third provides error-handling behavior. It is front-loaded with the core purpose and contains no filler.

  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?

  With an output schema present, a fully self-documenting source parameter schema, and rich annotations, the description covers everything an agent needs to select and invoke the tool correctly. It even includes quota/rate-limit handling, which is often missing.

  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%, and the source parameter already carries extensive, source-specific validation guidance. The description adds only the general constraint of 'one keyword and one source,' which is helpful but does not materially expand parameter semantics 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 states a specific action and resource: 'Full historical series for one keyword and one source (0-100 values, plus volume when available).' It also explicitly differentiates itself from sibling tools by naming get_top_trends and get_growth, so an agent can distinguish it immediately.

  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?

  It gives explicit when-to-use guidance: 'Use for charting or custom math.' It also provides exclusions: 'Not for live trending boards (use get_top_trends)' and 'For most growth questions, use get_growth.' The rate-limit handling instruction adds operational guidance.

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

• get_top_trendsA
  4.9/5.0
  Behavior5/5

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

  Annotations already mark the tool as read-only, open-world, and idempotent. The description adds meaningful behavioral context beyond that: 'No keyword', default sort behavior, the rank_change/window mechanics, the fact that store boards are not keyword lookups, and how to respond when rate limits or quota are exhausted. This is exactly the kind of extra operational behavior an agent needs.

  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 longer than average, but every sentence earns its place: purpose, category constraint, sort behavior, app-store nuance, sibling routing, and rate-limit handling. It is front-loaded with the core purpose and keeps the content organized so no sentence is redundant.

  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 six parameters, an output schema, and rich annotations, the description covers everything an agent needs: when to use it, how to select the right feed, how sort and window interact, which siblings to route to, and how to handle quota failure. The schema handles the valid enum-like type values and output structure, so the description does not need to repeat them.

  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 the baseline is 3. The description adds value by clarifying parameter interplay: category is mandatory for specific types, sort has two meaningful modes, window applies only to rank_change, and store feed types are live boards rather than keyword searches. It slightly exceeds the schema's own parameter descriptions without fully re-explaining every field.

  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?

  Uses a specific verb ('get') with a clear resource ('live top-trending board') and adds a sharp scope constraint: exactly one feed type and no keyword. It also draws an explicit line against the sibling tools by pointing to get_growth/get_time_series for app history, so an agent can distinguish this from the alternatives.

  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?

  Provides explicit routing: use category for certain feed types, use sort='rank_change' for climbers, and use get_growth or get_time_series for app history instead of this tool. It even says 'Do not use get_time_series for live boards,' which gives a clear exclusion. The rate-limit/quota instruction also tells the agent what to do in a failure case.

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