Gemini Deep Research Tool

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

With no annotations, the description carries the full burden. It usefully discloses the execution model ('completes in a single call; result returned immediately'), which matters because a polling sibling exists — but it omits cost, latency expectations for deep research, and any permission or rate-limit context.

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?

Three short sentences, front-loaded with the core action and no redundant restatement of the name. 'Using a specialized Gemini model' is mildly expendable but not wasteful.

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 return values need no explanation, and the input is fully documented. However, for a tool sitting in a cluster of research-related siblings, the description does not help the agent route between start/check/followup, leaving a real 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?

Single parameter at 100% schema coverage, so the schema already defines 'query' as 'The research question or topic.' The description adds no syntax, length, or formatting guidance beyond that 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?

States a clear verb+resource ('Start a deep research task') and adds scope ('multi-step web research to answer complex questions'), so the agent knows this initiates research rather than checking on or extending it. It stops short of naming the sibling tools (gemini_check_research_tool, gemini_research_followup_tool) that a caller would need to distinguish it from.

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 phrase 'to answer complex questions' implies when the tool is appropriate, but there is no explicit when-not guidance and no mention of the check/followup siblings. Usage context is inferable but not directed.

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