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

Beyond the annotations (readOnly, openWorld, idempotent=false, non-destructive), the description discloses non-obvious behavioral facts: results are licensed for immediate use only (Brave terms), failed calls are free while every successful call costs $0.01 via x402 USDC or card key, and repeats are not free. Those billing and licensing constraints materially change how an agent should plan retries and caching, and none of them appear in structured fields.

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 purpose and cost model are front-loaded, and each sentence carries operational information. There is minor redundancy: 'failures are uncharged' and 'failed calls free' repeat the same fact, and 'each call is charged, so repeats are not free' restates the price line.

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?

For a 15-parameter tool with no output schema, the description covers purpose, returned fields, optional enrichments, filtering, pricing, licensing and failure behavior, which is close to sufficient. It stops short of describing the shape of highlight/summary objects or pagination/count semantics, so an agent still relies on the schema for output expectations.

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 100%, so the baseline is 3; the description goes slightly beyond by grouping the optional capabilities into named feature families (page text, highlights, per-result summary, and domain/date/category filters). It adds no per-parameter detail for count, numSentences, highlightsPerUrl, includeText or excludeText, so it is a mild improvement rather than a full semantic layer.

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 gives a specific verb plus resource ('search the web and get the top results as JSON') and enumerates the returned fields (title, URL, snippet, published date, domain), so the tool's function is unmistakable. It does not, however, distinguish itself from close siblings such as 'search', 'news_search', 'papers' or 'wikipedia', so an agent must infer the boundary on its own.

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 an agent needs current information, sources or links from the open web' plus the concrete example 'q=x402 payment protocol' gives clear positive guidance on context of use. There are no explicit exclusions or named alternatives for cases like news-only or academic lookups, which is the main gap given the many overlapping siblings.

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