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

Annotations declare readOnlyHint=true and openWorldHint=true, so the agent already knows this is a safe read operation. The description adds valuable behavioral context beyond the annotations: it warns that the tool is slow (answers generated per request), explains the continuable token mechanism and its 30-minute expiry, and notes that image_url cannot combine with a token. These are exactly the kind of behavioral traits an agent needs to know. It doesn't describe rate limits or failure modes, but the annotations already cover the safety profile, so a 4 is appropriate.

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 description is three sentences with zero waste. The first sentence front-loads the core purpose and output format, the second explains the two most important optional parameters, and the third delivers the critical behavioral warning (slow) and the auth requirement. Every sentence 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?

For a tool with 11 parameters, 100% schema coverage, and no output schema, the description is quite complete. It covers the core purpose, output structure, the continuable follow-up mechanism, the image_url constraint, the slowness warning, and the API key requirement. The only gaps are minor: it doesn't explain what happens with result_groups filtering or the uule/location conflict, but those are documented in the schema. The description is complete enough for an agent to call this tool 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 description coverage is 100%, so the schema already documents all 11 parameters. The description adds meaning for a few key parameters: continuable (get a token for follow-up questions), image_url (adds a picture to the prompt), and subsequent_request_token (implied by the follow-up explanation). However, it doesn't add much beyond the schema for parameters like gl, hl, uule, device, location, google_domain, or result_groups. Since the schema does the heavy lifting, the baseline 3 is correct.

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 ('Ask'), a specific resource ('Google AI Mode'), and the exact output shape (ordered text_blocks with sources). It also names the sibling tool google_ai_overview implicitly by distinguishing AI Mode from a plain search, and the sibling list confirms this is the AI-powered Q&A tool rather than a generic search. The description is unambiguous about what this tool does and how it differs from the 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?

The description gives clear context for when to use this tool: when you want a generated answer with cited sources, and it explicitly warns that it is slow because answers are generated per request. It also explains the continuable token mechanism for follow-up questions, which is a key usage pattern. However, it does not explicitly name alternatives or state when NOT to use this tool (e.g., when you need fast results, use google_search instead). The sibling list provides context but the description itself doesn't draw the contrast.

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