Perplexity Agent Research

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.

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.

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.

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.

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.

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.