Deep Research

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by warning that this tool is 'Significantly slower than other tools (can take minutes)' and by noting it returns 'a detailed response with numbered citations.' This gives the agent critical execution-time expectations.

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 and front-loaded, with each sentence earning its place. It covers the core function, use cases, return characteristics, performance caveat, and sibling alternatives without any filler or repetition.

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?

The description is complete for an AI agent selecting and invoking the tool: it explains operation, when to use it, performance trade-offs, and the return shape (numbered citations). The presence of an output schema means the structure of the return value does not need to be described here. A small gap is that it does not mention input length or message-format constraints, but the schema already covers the required messages field.

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%, and the messages parameter is already fully described in the schema as an array of conversation messages. The description's reference to 'a topic' adds only light context and does not substantially enrich the meaning of the messages parameter beyond what the schema 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 uses a specific verb and resource: 'Conduct deep, multi-source research on a topic' and immediately scopes it with 'Perplexity Agent API, high preset.' It also distinguishes itself from siblings by naming the best-use cases: literature reviews, comprehensive overviews, and investigative queries needing many sources.

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 provides explicit when-to-use guidance with concrete examples: 'Best for: literature reviews, comprehensive overviews, investigative queries needing many sources.' It also gives clear routing instructions by stating when NOT to use it: quick factual questions should use perplexity_ask, and logical analysis should use perplexity_reason.

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