tavily_research

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

With no annotations provided, the description carries the full burden and covers key operational traits: async execution, 1-5 minute latency, and a 20 requests-per-minute rate limit. These are not in the schema or annotations and are valuable. It does not mention errors, costs, or idempotency, but the most critical behavior is transparent.

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 three sentences with each serving a distinct purpose: purpose, usage trigger, and behavioral warning. No filler or redundancy; the critical async and rate-limit info is placed last without distracting from the core purpose.

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 the main purpose, usage trigger, and critical behavioral constraints, and the presence of an output schema covers return values. However, it does not clarify the relationship to sibling tools or explain the meaning of optional parameters (e.g., output_length, citation_format, domain filters), leaving some operational gaps for a complex tool.

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%, so the description must compensate, but it provides zero parameter explanations. While parameter names (input, model, output_length, citation_format, include/exclude_domains) are somewhat self-explanatory, the description adds no meaning beyond the schema's own titles and enums, leaving the agent to infer usage.

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 verb-resource pair ('perform comprehensive research') and defines the input as a topic or question, with a clear output expectation. It hints at differentiation from siblings by emphasizing multiple sources, but does not explicitly name sibling distinctions.

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?

It provides an explicit trigger condition: 'when you need to gather information from multiple sources to answer a question.' This gives clear context, but it lacks negative guidance or explicit alternatives (e.g., when to prefer tavily_search or tavily_extract), so it does not fully meet the highest bar.

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