Server Quality Checklist

Tool Scores

• perplexity_agentA
  4.2/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint=false and openWorldHint=true, so the description carries less burden. It adds valuable nuance by disclosing the blocking behavior (wait=true) and the timeout fallback that yields a response_id—useful context for an agent deciding how to invoke the 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 compact—two sentences—and front-loaded with the action and primary use case. It includes essential behavioral details without any filler, every sentence 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 tool's complexity (5 params, no output schema), the description covers purpose, use case, and key blocking behavior. It references the response_id and the result tool, helping the agent understand the workflow. It could be more complete by mentioning cancel behavior or result format, but these are secondary.

  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 adds a small nuance for the wait parameter (timeout also yields a response_id) but does not add meaningful detail for preset, domains, or recency beyond what the schema already provides.

  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 action with 'Run a research query through Perplexity's Agent API (multi-step web research with citations)'—a specific verb and resource. It also distinguishes itself from siblings by explaining the response_id flow for later collection with perplexity_agent_result.

  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 gives explicit context with 'Use for deep or multi-hop questions where a single synthesized, sourced answer is wanted.' It also explains when to set wait=false for parallel queries and mentions the fallback to perplexity_agent_result, though it does not mention perplexity_agent_cancel.

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

• perplexity_agent_cancelA
  4.2/5.0
  Behavior4/5

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

  Annotations already mark this as destructive, and the description adds the behavioral nuance that Perplexity does not report usage for cancelled runs, so the billing impact is unknown. This goes beyond the structured annotation by explaining a consequence of the operation.

  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 short sentences, front-loaded with the action and followed by a relevant caveat. No redundant phrasing.

  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?

  For a simple one-parameter cancel operation, the description covers the action, the trigger condition, and a key side-effect caveat. It doesn't specify the return value, but no output schema exists and the behavior is sufficiently clear.

  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 only parameter (response_id) is already fully described in the schema, so the description doesn't need to add more. It correctly references where the ID comes from, matching 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 uses a specific verb ('stop') and resource ('a research run') and clearly distinguishes from sibling tools (perplexity_agent, perplexity_agent_result) by focusing on cancellation. Title 'Cancel Perplexity Research' reinforces the action.

  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 states when to use it ('when no longer needed'), giving clear contextual guidance. It does not explicitly name alternatives or exclusions, but the sibling tool names make alternative uses obvious.

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

• perplexity_agent_resultA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the description adds value by mentioning that if the run is still running, it reports progress and how to check again. This is useful context not covered by the annotation alone.

  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 'Retrieve', and contains no redundant or irrelevant information. Every sentence 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?

  For a simple retrieval tool with two parameters and no output schema, the description covers the main use case and the pending-state behavior. It doesn't specify the return format, but that is not essential given the tool's simplicity and the lack of an output schema.

  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 both response_id and wait_seconds having detailed descriptions including clamping behavior. The description adds no extra parameter semantics beyond what the schema already provides.

  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 retrieves the result of a research run started by perplexity_agent, which is a specific verb+resource. It distinguishes from the sibling cancel tool and the initiating tool by focusing on result retrieval.

  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?

  It implies usage after perplexity_agent has started a run and explains the behavior if the run is still running. However, it doesn't explicitly mention when not to use it or directly name alternatives beyond the sibling tool list.

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