Server Quality Checklist

Tool Scores

• get_top_trendsA
  4.4/5.0
  Behavior4/5

  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. The description adds behavioral context beyond those: it clarifies the tool is not a keyword lookup, distinguishes live store boards from keyword-style queries, and discloses rate-limit/quota handling ('tell the user their plan limit is 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 description is a dense paragraph with no filler — purpose, category rule, sort/window behavior, sibling routing, and quota handling each carry real signal. It is on the longer side and could be broken into clearer segments, but every sentence 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?

  With a full output schema and 100% parameter coverage, the description's remaining job is selection and invocation context, which it covers thoroughly: which feeds are live boards, which types require category, how sort and window interact, and where to route non-live-board queries. Nothing an agent needs to call this tool 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?

  Schema description coverage is 100%, so the baseline is 3 and the description need not re-document parameters. It does reinforce key semantics — 'always pass category' for four types and the 'only omit on a first pull to learn official names' nuance — but most of its parameter mentions (window values, sort modes) mirror what the schema already states.

  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 — 'Live top-trending board for exactly one feed type' — and immediately adds a discriminative constraint ('No keyword') that separates it from keyword-search tools. It also names sibling tools and explicitly routes app-history queries to get_growth or get_time_series, making differentiation unambiguous without opening any schema.

  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 explicit when-to-use guidance: always pass category for four named types, and use sort='rank_change' with a valid window for climbers. It also states clear exclusions ('Do not use get_time_series for live boards'), names the alternatives for app history, and tells the agent how to behave when rate limits or quota are hit.

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

• get_time_seriesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare the tool read-only, open-world, and idempotent. The description adds value beyond that by disclosing the response size (0-100 values) and that volume may be included when available. It also reveals behavior under rate limiting/quota exhaustion, telling the agent to inform the user their plan limit is 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.

  Conciseness5/5

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

  Every sentence earns its place: core behavior, use cases, sibling routing, and error behavior are covered in four short sentences. The critical scoping constraint ('one keyword and one source') is front-loaded, and the sibling alternatives are clear and immediately actionable.

  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 two-parameter read-only tool with a full output schema and 100% schema coverage, the description provides everything else an agent needs: purpose, use cases, exclusions, sibling routing, response limits, and error handling. Nothing essential 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?

  Schema description coverage is 100%, so the schema already thoroughly documents both parameters, including detailed per-source keyword format rules. The description confirms 'one keyword and one source' but adds little semantic detail beyond the schema. Baseline 3 is appropriate since the schema carries the burden.

  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 first sentence clearly states the tool returns a full historical series for one keyword and one source, which is a specific resource and operation. It also explicitly distinguishes itself from siblings: it is not for live trending boards (use get_top_trends) and not for most growth questions (use get_growth). This makes the tool's purpose unambiguous relative to the sibling set.

  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 explicit when-to-use guidance ('Use for charting or custom math') and when-not-to-use guidance with named alternatives ('Not for live... (use get_top_trends)'; 'For most growth questions, use get_growth'). It also instructs the agent on quota/rate-limit handling, which is a rare and valuable usage detail.

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

• get_growthA
  4.7/5.0
  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 valuable behavioral context beyond those hints: values are on a 0-100 scale, absolute volume is included when available, and the tool may hit rate limits requiring a user-facing plan-limit message.

  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 and front-loaded: the core behavior appears first, followed by data-scale context, sibling differentiation, and error handling. Every sentence contributes meaningful guidance without redundancy.

  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 read-only growth tool with a rich output schema, the description covers the essential context: behavior, output scale, source caveats, sibling relationships, and rate-limit handling. Nothing critical is missing for an agent to select and 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?

  Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description lightly reinforces the preset-window concept and the Android bundle ID requirement for app sources, but it does not need to compensate for missing schema detail.

  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 further distinguishes itself from siblings by explicitly saying to prefer it over get_time_series for growth questions and clarifying app sources are not the live boards on get_top_trends.

  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 explicit routing guidance: 'Prefer this over get_time_series for growth questions.' It also warns that app downloads/app rankings sources should not be confused with get_top_trends, and instructs the agent on how to handle rate limits or quota exhaustion.

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