deep_research

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

With no annotations, the description carries the full burden and discloses meaningful behavioral details: it returns a citations list with stable [n] numbers and an evidence list of per-source markdown, and it performs no LLM synthesis. It does not explain tradeoffs of 'prefer' modes or rate/stealth behavior, but the core behavior is clearly communicated.

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 well-structured: it leads with the core behavior, then the return format, then use cases, and finally parameters. Every sentence serves a purpose and the format is scannable for an AI agent.

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 covers purpose, output shape, and parameter basics, which is solid, but it leaves gaps: the meaning of the 'prefer' options is opaque, and there is no guidance on rate limits, cost, or when to avoid this tool in favor of a lighter sibling. These gaps matter for correct invocation in an agent context.

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 0%, and the description compensates with an Args block explaining query, limit, scrape_top, and prefer. Each parameter gets some semantic context beyond the schema, though 'prefer' only lists options without explaining what they mean in practice.

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 states a specific behavior: 'Search the web, then pull the top sources as EVIDENCE'. It distinguishes itself from a plain web search by emphasizing the evidence/citations output and the absence of LLM synthesis, which sets it apart from sibling search tools.

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 clearly states when to use it: 'Designed for research, RAG prep, and fact-checking.' It also signals that this tool returns raw evidence for the agent to synthesize, implying the right use case. However, it does not explicitly contrast with alternatives like 'search' or 'search_papers'.

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