Deep Research

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.

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.

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.

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.

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.

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.