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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds material behavioral context beyond that: a $0.02/call cost, an independent search index, freshness-filter semantics, the fact that results are untrusted external content, and the output shape. It clearly warns that results should be analyzed rather than treated as instructions, which is essential for an open-web search tool.

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 dense and front-loaded: it delivers the core action, cost, output format, use case, alternatives, untrusted-content warning, and payment options in a compact block. Every segment earns its place, especially for a monetized external-data tool where the agent must understand cost and trust before calling it. The length is appropriate for the information it conveys.

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 provided output schema covers the return value, and the description nevertheless summarizes return fields as well as cost, freshness behavior, untrusted content, and optional alternatives. There is no likely missing context that would prevent an agent from invoking the tool correctly for typical web discovery tasks.

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?

Input schema coverage is 100%, so the schema already documents q, count, and freshness with basic types and defaults. The description adds value by expanding freshness values (pd/pw/pm/py = past day/week/month/year), giving the max-400-char behavior context, and explaining the output composition without repeating the full schema. This is solidly above the baseline but not a unique manual for every parameter.

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 specific verb-resource pair: live web search returning ranked results (title, URL, snippet, age) from an independent index. It also positions itself against siblings by saying 'Start here to DISCOVER pages' and directing current-events queries to search-news and synthesized answers to answer, so an agent can distinguish it from the other web tools.

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 gives an explicit usage path: start here to discover pages, then read the winner with extract. It names alternatives for distinct use cases—search-news for current events, answer for cited synthesized answers—and even provides cost guidance about multi-search for several queries at once. This clearly helps an agent know when to select this tool versus siblings.

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