Server Quality Checklist

Tool Scores

• perplexity_researchA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the description's addition of 'Significantly slower than other tools (30+ seconds)' and 'Returns a detailed response with numbered citations' provides valuable behavioral context beyond the structured metadata. It does not contradict the read-only nature.

  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 compact set of five purposeful sentences. It front-loads the core action, then provides use cases, output format, a performance warning, and sibling alternatives—all without 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?

  With an output schema present and annotations providing read-only safety, the description gives sufficient context: purpose, use cases, speed, and alternatives. It is complete for a research tool, though it could mention specific limitations of the underlying model or cite that responses are not real-time.

  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%, so the baseline is 3. The description does not describe parameters directly, but the schema already documents messages, strip_thinking, and reasoning_effort with their meanings. The description's reference to 'deep research' implicitly aligns with reasoning_effort, but adds no new parameter-level 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 clearly states the tool conducts deep, multi-source research on a topic, and explicitly distinguishes it from siblings by naming alternatives for quick facts and logical reasoning. It also adds concrete output characteristics like numbered citations.

  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?

  Explicit when-to-use guidance is provided: 'Best for literature reviews, comprehensive overviews, investigative queries needing many sources.' It also clearly states when NOT to use it ('quick factual questions' -> use perplexity_ask; logical analysis -> use perplexity_reason) and warns about the 30+ second latency.

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

• perplexity_askA
  4.5/5.0
  Behavior4/5

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

  Annotations indicate read-only, open-world, non-destructive behavior. The description adds context beyond annotations: returns numbered citations, supports specific filter types, and notes speed/cost trade-offs. It does not contradict annotations, and the added behavioral details are valuable for expectation-setting.

  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: purpose, use cases, output format, performance, filters, and alternatives. It is front-loaded and clearly structured, with no wasted words despite covering multiple facets.

  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 the tool's moderate complexity, the presence of an output schema, and rich annotations, the description covers all essential aspects: operation, output, configuration, and tool differentiation. It is fully sufficient 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 parameter semantics are already documented. The description restates filter types (recency, domain, context size) but does not meaningfully enrich beyond the schema's own descriptions. Baseline 3 is appropriate because 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 description opens with a specific verb and resource: 'Answer a question using web-grounded AI (Sonar Pro model).' It clearly contrasts with sibling tools by naming perplexity_research and perplexity_reason, making the tool's specific role unmistakable.

  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 'Best for' scenarios (quick factual questions, summaries, explanations, general Q&A), performance expectations ('Fastest and cheapest'), and direct alternatives ('For in-depth multi-source research, use perplexity_research instead'). This gives agents clear when-to-use and 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.

• perplexity_reasonA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds useful behavioral context beyond annotations, such as the reasoning model ('Sonar Reasoning Pro model'), the step-by-step nature of the analysis, and the presence of numbered citations in the output. These details help the agent anticipate response style and value. However, it doesn't explicitly mention potential latency or token usage, which could be relevant for a reasoning-heavy tool.

  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 concise and well-structured, with four sentences covering purpose, usage cases, output features, and alternatives. It is front-loaded with the core function and uses no filler. Every sentence adds valuable information, making the description efficient and easy to parse.

  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 the tool's complexity (5 params, output schema, annotations), the description is complete: it covers what the tool does, when to use it, when not to use it, and what to expect in the response. The output schema exists, so return values need not be described. The combination of annotations, schema, and description provides a comprehensive picture.

  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%, with all 5 parameters thoroughly documented in the schema. The description mentions 'Supports filtering by recency (hour/day/week/month/year), domain restrictions, and search context size,' which echoes schema properties without adding new semantic depth. It does not explain parameter interactions or provide extra context beyond the schema, so a 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 clearly states the tool's function: 'Analyze a question using step-by-step reasoning with web grounding (Sonar Reasoning Pro model).' It distinguishes itself from siblings by specifying its niche: 'Best for: math, logic, comparisons, complex arguments, and tasks requiring chain-of-thought.' It also notes the return format: 'Returns a reasoned response with numbered citations.' This is a specific verb+resource+scope with clear differentiation.

  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 provides explicit usage guidance, stating 'For quick factual questions, use perplexity_ask instead. For comprehensive multi-source research, use perplexity_research instead.' It also lists ideal use cases ('Best for: math, logic, comparisons...'), giving the agent clear criteria for when to choose this tool over alternatives.

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

• perplexity_searchA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful behavioral context: results are ranked, formatted with specific fields, and there is no AI synthesis. It does not discuss pagination or rate limits, but the annotation coverage lowers the burden.

  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?

  Four short sentences each earn their place: purpose+output, use cases, behavioral caveat, and sibling alternative. Front-loaded with the core purpose, no fluff 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?

  Given the rich annotations (readOnly, openWorld, non-destructive), a high-coverage schema, and the explicit mention of result format and alternative tool, the description is complete for this search tool. It covers what the tool does, when to use it, what it returns, and how it differs from the key sibling.

  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 four parameters (query, country, max_results, max_tokens_per_page) are documented in the schema. The description adds no additional parameter-level meaning beyond what the schema 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?

  Description opens with a specific verb+resource: 'Search the web and return a ranked list of results with titles, URLs, snippets, and dates.' It clearly states the output format and adds 'no AI synthesis,' which distinguishes it from the sibling perplexity_ask tool.

  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?

  'Best for: finding specific URLs, checking recent news, verifying facts, discovering sources' explicitly defines intended use cases. It also provides an explicit alternative: 'For AI-generated answers with citations, use perplexity_ask instead.' This meets the when/when-not guidance standard.

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