realtime_web_search

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

With no annotations, the description carries the transparency burden. It does disclose output types and required parameters per operation, but it omits operational details like rate limits, pagination, or the differences between search, search_full, and search_light. The use of 'SERP' adds context, but deeper behavioral traits remain unspecified.

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 concise and well-structured: a one-sentence purpose, a bulleted operation list, and a short usage note. It is front-loaded with the most important information and contains no redundant or filler text.

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 tool's overall purpose and available operations, but it does not explain when to choose specific operation variants (e.g., search vs search_full) or describe the return format/pagination for the variant responses. Given the absence of an output schema, this leaves notable gaps for an agent deciding which operation to invoke.

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?

The input schema's parameter descriptions are generic and explicitly defer to the tool description for required params. The description compensates by listing each operation with its required parameter names (q, queries, prompt) and clarifies that args is a key/value container. This adds substantial meaning beyond the schema, though it does not explain parameter nuances beyond their names.

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 performs real-time Google web searches (SERP) and enumerates specific result types (organic results, knowledge panels, AI Overviews). It distinguishes itself from siblings by explicitly naming alternatives for news and autocomplete, leaving no ambiguity about its core function.

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?

A dedicated 'When to use' section explicitly directs users to realtime_news_data for news and web_search_autocomplete for autocomplete, while positioning this tool for general web/Google searches. The list of operations further implies different use cases, giving clear contextual guidance.

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