web_search

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

With no annotations, the description discloses the API key dependency and the no-fallback behavior. It also hints at optional synthesis (include_answer). It does not cover rate limits or error handling, but the key requirement is a critical behavioral trait.

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?

Two sentences, no filler, front-loaded with the core capability. Every clause adds value.

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 5 parameters and 0% schema coverage, the description is incomplete on parameter details. However, it covers the essential output and the critical dependency. The presence of an output schema reduces the need to describe return values.

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 0%, so the description should compensate by explaining parameters. It only mentions that query is required and include_answer provides an optional answer, but leaves max_results, search_depth, and topic undocumented.

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 action (search the web with Tavily) and the output (titles, URLs, snippets, optional answer). It distinguishes from the sibling tool web_fetch by its focus on search versus fetching a specific URL.

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 explicitly states the environment requirement (TAVILY_API_KEY) and warns of no fallback, which guides when the tool is usable. However, it does not explicitly contrast with web_fetch or provide alternative scenarios.

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