Server Quality Checklist

Tool Scores

• perplexity_askA
  4.5/5.0
  Behavior4/5

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

  Annotations already mark readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds that it returns 'text response with numbered citations' and supports filtering by recency, domain, and context size. No contradictions. Slight room for improvement: could mention it's stateless or that citations are always numbered.

  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 tightly packed sentences plus a concise enumeration of filtering options. Purpose is front-loaded, no filler. 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?

  Given 4 parameters, existing output schema, and rich annotations, the description covers all key aspects: purpose, usage, alternatives, return format, and filtering. No gaps remain for an agent to misinterpret.

  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% with good descriptions for each parameter (e.g., enum values for search_recency_filter). The description mentions filtering capabilities but does not add significant extra meaning beyond the schema. Baseline 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 specifies the action ('Answer a question'), the resource ('web-grounded AI (Sonar Pro model)'), and concrete use cases (quick factual questions, summaries, explanations, general Q&A). It explicitly differentiates from siblings by naming alternatives (perplexity_research, perplexity_reason) and their respective strengths.

  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 clearly states when to use this tool (best for quick factual questions, summaries, etc.) and when not to (in-depth research → use perplexity_research; step-by-step reasoning → use perplexity_reason). It also highlights speed and cost ('fastest and cheapest option'), providing complete guidance.

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

• perplexity_researchA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and destructiveHint=false, but description adds behavioral context: 'Significantly slower than other tools (30+ seconds)' and 'Returns a detailed response with numbered citations', which are not in annotations. 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?

  Three sentences with no fluff: first defines purpose, second lists best use cases, third addresses speed and output format. Each sentence adds value.

  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 has 3 parameters, output schema, and annotations, the description covers purpose, usage context, behavioral trait (slowness), and output format. No gaps.

  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 parameters are fully documented in schema. Description does not add parameter-specific meaning, which is acceptable given high coverage.

  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 clearly states the tool conducts deep multi-source research, cites literature reviews and comprehensive overviews as use cases, and distinguishes from sibling tools by contrasting with perplexity_ask and perplexity_reason.

  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?

  Explicitly provides when to use (literature reviews, comprehensive overviews, investigative queries needing many sources) and when not to use (quick factual questions → perplexity_ask; logical analysis → perplexity_reason), with sibling tool names.

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

• perplexity_reasonA
  4.7/5.0
  Behavior4/5

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

  Annotations already provide readOnly, destructive, idempotent, and openWorld hints. The description adds behavioral context about the reasoning model (Sonar Reasoning Pro), step-by-step reasoning, and return format (numbered citations), which goes beyond 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 well-structured sentences: first sentence states purpose and model, second gives best uses, third mentions return format and filters, fourth gives alternatives. No wasted words, information is front-loaded.

  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 complexity (5 params, 1 required, 100% schema coverage, output schema exists), the description sufficiently covers purpose, usage, and filtering options. Output schema handles return value details, so no further explanation needed.

  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% with descriptions for all 5 parameters. The description adds context by summarizing filtering capabilities (recency, domain, context size) and their purpose, enhancing understanding 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 clearly states 'Analyze a question using step-by-step reasoning with web grounding', specifying a specific verb and resource. It distinguishes from siblings by mentioning alternative tools for quick facts and comprehensive research.

  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?

  Explicitly states best use cases (math, logic, comparisons, complex arguments, chain-of-thought) and provides clear alternatives: 'For quick factual questions, use perplexity_ask instead. For comprehensive multi-source research, use perplexity_research instead.'

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

• perplexity_searchA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint true and destructiveHint false. The description adds that the tool does no AI synthesis and returns formatted results, which is consistent and helpful beyond the 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?

  The description is extremely concise with two sentences and a bullet-like phrase. It is front-loaded and every sentence adds value.

  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 simplicity (1 required param, 4 total) and the presence of annotations and output schema, the description is complete enough to guide correct use.

  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 description adds little beyond the schema. It does not elaborate on parameter meanings, but the schema already provides adequate descriptions. A 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 verb 'search', the resource 'the web', and the output format. It distinguishes itself from the sibling tool perplexity_ask by noting that this tool returns formatted results without AI synthesis.

  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 explicitly lists best use cases (finding URLs, checking news, verifying facts) and provides an alternative for AI-generated answers with citations (perplexity_ask).

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