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

Annotations already declare readOnly, openWorld, non-idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely useful non-annotation context: per-call pricing (US$0.02), a daily free-call cap, and the notable guarantee that every returned URL is verified against actual search results with the answer drawn only from those pages.

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 'Use when', but the phrasing is run-on and redundant ('find pages on the live web: search the live web'), and pricing/limit details are appended in terse fragments. Content mostly earns its place but the structure is cluttered with repetition.

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?

With an output schema present, return values need not be re-explained, yet the description usefully covers the result shape, the answer behavior for questions, cost/limits, and the site filter. For a read-only search tool this is essentially complete, with only alternative-tool routing missing.

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 q, max, and site are already documented in the schema. The description only echoes the optional site filter and adds no syntax, format, or default details beyond what the schema provides; baseline 3 applies.

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 and resource ('search the live web') and describes the return shape (title, URL, snippet, best-first, plus a short answer for question queries). This is enough to distinguish it from read_pages, but the description never explicitly contrasts the two, so sibling differentiation is left to inference.

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?

'Use when you need to find pages on the live web' gives a clear trigger context. However, no when-not conditions or named alternatives (e.g., read_pages for already-known URLs, quick_ai) are provided, leaving the agent to figure out routing on its own.

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