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

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), the description discloses operationally important behavior: a hard cap of 5 results, per-page truncation at 20,000 characters, that unfetchable pages are dropped and refunded, and that the call is paid in stablecoins. These cost and failure-mode details are exactly what an agent needs and are not derivable from 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?

The core is a single dense, front-loaded sentence, and follow-on sentences cover limits, refunds, and pricing. It is slightly run-on and the 'for AI agents' framing is filler, but virtually every clause carries usable information.

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 no output schema and only two parameters, the description fully compensates: it enumerates the returned fields, the truncation limit, the result cap, the failure/refund behavior, and the payment model. An agent can call this correctly without opening anything else.

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 both parameters are fully documented in the schema including the limit clamping rules and the query format. The description only lightly reinforces this ('Up to 5 results'), so the baseline 3 applies — it neither adds much nor is needed to.

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 states a specific verb and resource ('web search with page content'), and specifies the return shape: title, URL, short description, and page text as Markdown. It does not explicitly differentiate itself from the sibling 'google-search' or 'google-news', leaving the agent to infer that this tool fetches full page content while those return listing-style results.

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?

There is no explicit when-to-use or when-not-to-use guidance. The phrase 'for AI agents' and 'in one call' hint at the value proposition but never name an alternative tool or state the conditions that select this one over the many search-shaped siblings.

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