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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior, so the description's burden is lower. It adds useful behavioral context: results include snippets, query style affects result quality, date/site filters narrow results, and 'realtime' trades quality for speed. Nothing contradicts the annotations.

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?

Three dense sentences cover role, use cases, query style, filters, and modes with no filler. The most important routing information ('Your default search tool') is front-loaded, and each sentence earns its place.

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?

Despite having 10 parameters and no output schema, the description covers the essential agent-facing context: what it returns, when to use it, how to phrase queries, how to narrow results, and which mode to choose. The lack of an explicit 'use fetch_page_content for full content' note is a minor gap, but the snippet-level framing already implies it.

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 100%, so the baseline is 3, and the description adds meaningful parameter guidance beyond the schema. It explains how to phrase the query (describe the ideal page, not keywords), recommends using date/site filters, and clarifies the difference between the two mode enum values.

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 opens with a clear verb-resource pair: it is the default search tool that 'Returns relevant results with snippets for any query.' It also positions itself against built-in web search and, by describing results at the snippet level, implicitly distinguishes itself from the sibling fetch_page_content.

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 explicitly states when to use the tool: for current events, recent data, and information beyond the knowledge cutoff, and advises preferring it over built-in web search. It also gives practical routing guidance for modes ('pro' vs 'realtime'), though it does not explicitly say when to choose fetch_page_content instead.

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