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

Annotations already declare readOnlyHint=true, non-destructive and openWorld, so the safety profile is covered. The description adds substantive behavior beyond that: the billing model ('one request for the search plus one per page read') and the exact shape of what is returned. Missing is any disclosure of failure modes, rate limits, or what happens when a page cannot be read.

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?

Two sentences, front-loaded with the action and the return shape, then the usage line, then the billing caveat. No filler or restatement of the title.

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, the description carries the burden of explaining returns and does so precisely: AI Overview when present, `results` pages as Markdown, other organic results as title/URL/snippet. Combined with the cost note, an agent has everything needed to decide and call correctly.

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, but the description earns an extra point by tying the `results` count to cost ('one per page read'), giving the parameter an implication the schema does not state. `proxy_country` and `keyword` are left entirely to the schema, which is acceptable at full coverage.

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?

Uses a specific verb-plus-resource framing ('Search Google... and read the top results in one call') and spells out the composite output: AI Overview, top pages as Markdown, and remaining organic results as title/URL/snippet. That composite shape is enough to tell it apart from plain search siblings like google_search without opening either schema.

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 it to answer a question from the live web' gives a clear positive selection criterion. It stops short of naming alternatives or exclusions, though — nothing tells the agent when plain google_search or fetch_markdown would be preferable.

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