Web Search

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

With no annotations, the description carries the burden well: it discloses the return shape (title, url, snippet), a conditional synthesized answer gated on TAVILY_API_KEY, and value ranges/defaults for max_results and topic. It omits error/rate-limit behavior and pagination, so it is strong but not complete.

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?

Front-loaded with the purpose and then the return behavior and constraints; every sentence carries information. Slightly dense with parameter details appended, but no 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?

An output schema exists, so return-value coverage is largely handled elsewhere. However, with 0% schema coverage and two similarly named count parameters ('limit' vs 'max_results'), the description does not fully specify what an agent should pass, leaving a genuine ambiguity.

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 document all four params. It explains max_results (1-10, default 5) and topic (general | news), but 'limit' and the relationship between 'limit' and 'max_results' are left entirely unexplained, which is a real gap.

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?

States a specific verb+resource ('Search the web') and narrows the intended use to how-to questions about apps, with a concrete query template ('how to <task> in <app> android'). This clearly distinguishes it from the entirely device-automation sibling set, none of which do web search.

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?

Gives a clear usage context (how-to-in-an-app queries) and the note that 'the screen overrules results' hints at result prioritization. It stops short of explicit when-not conditions or named alternatives, but the intended use case is unambiguous.

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