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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the bar is lower, yet the description adds material context: answers 'can take over a minute' (latency) and 'Billed $0.005 per request' (cost). It also discloses the continuation mechanism, which is behavior an agent must know before calling.

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?

Four tight sentences, front-loaded with the core action and output shape, then latency/cost/alternative. Every sentence carries information, though the output-shape parenthetical is slightly dense.

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 compensates by naming the return fields (reply_parts, reference_links) and covering latency, billing, and session continuation. An agent has everything needed to decide and invoke 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 prompt, country, language, and session_token are already documented in the schema. The description reinforces session_token's conversational-continuation meaning but adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource ('Ask Google AI Mode a prompt') and enumerates the shape of the answer (reply_parts: paragraphs, headings, lists, images) plus citations. This distinguishes it cleanly from the many search_* siblings without opening a 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?

Explicitly routes the agent: 'Use search_web for plain search results,' and describes the follow-up flow via session_token. The condition selecting this tool (AI-synthesized answers vs. plain results) is stated, not implied.

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