Google Ai Mode

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

With annotations covering the safety profile (readOnly, idempotent, openWorld, non-destructive), the description adds genuinely novel context: Google rate-limiting, the fact that blocked results require waiting or switching tools, and that the AI Mode page nearly always needs JS so engine=auto falls back to browser. That is real behavioral value beyond 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?

Front-loaded with the purpose and result shape, then engine notes, then rate-limit guidance — three tight blocks with no filler. Slightly fragmented by mixing languages and a parenthetical cross-reference, but every line earns its place.

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?

An output schema exists, so the description needn't explain return values, and it is complete on rate-limiting, engine selection, and JS fallback. The main gap is that the localization parameters (gl/hl) are undocumented anywhere, leaving an agent guessing about their meaning.

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 0% with 4 parameters, so the description carries the burden. It usefully documents the engine parameter's values (auto|http|proxy|browser) and the JS/browser fallback behavior, which the schema does not express. But gl, hl, and query are left entirely unexplained, so compensation is only partial.

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+resource with scope: a Google AI Mode (udm=50) synthesis search returning 'answer + sources', positioned for 'pertanyaan langsung' (direct questions). It distinguishes itself contextually from generic listings and references the sibling google_web_search for engine semantics. It stops short of an explicit contrast with the many other search siblings.

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?

It gives implied usage ('cocok untuk pertanyaan langsung') and explicit failure-path guidance ('when the result is blocked, wait or switch to an RSS-based tool'), which names an alternative class of tool. However there is no clear when-not-to-use statement or routing rule against the concrete siblings (google_web_search, google_search).

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