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

Annotations already mark the tool read-only; the description adds valuable context beyond that: it returns null when no AI Overview exists, returns only the ai_overview block in a specific structure, and requires an API key. It doesn't cover failure modes, but with readOnlyHint and openWorldHint present, this is strong.

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 with no wasted words: the core behavior is front-loaded, followed by the null case and the auth requirement. Every clause adds useful 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?

For a 24-parameter tool with no output schema, the description is reasonably complete: it gives the return shape, the null case, and authentication. It could say more about which google_search parameters actually influence AI Overview generation, but the comprehensive parameter schema compensates for that gap.

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%, with all 24 parameters individually documented. The description's phrase 'Accepts the google_search parameters' adds only a grouping cue and no per-parameter meaning, so it meets but does not exceed the baseline.

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: 'Return only the AI Overview Google generates for a search,' and defines the output shape ('ai_overview with ordered text_blocks and cited references') plus the null case. This clearly distinguishes it from general search tools like google_search.

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?

The description implies this tool is for retrieving only Google's AI Overview and notes it 'Accepts the google_search parameters,' giving some context. However, it never explicitly names alternatives like google_search or google_ai_mode, nor states when not to use this tool, so routing is left to inference.

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