Gemini web research

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

The annotations already declare readOnlyHint and openWorldHint, but the description adds context about enabling Google Search and URL Context, and clarifies that prompts should contain URLs. This is meaningful behavioral information not present in the annotations, though it does not cover potential limitations or output format.

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 sentences, each delivering essential information: what the tool does, how to format prompts, and when to use alternatives. No wasted words.

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 simple single-param tool with no output schema, the description provides sufficient context about tool behavior and usage boundaries. The annotations cover safety profile, and the description covers usage and alternatives, making it complete.

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?

The schema already describes the 'prompt' parameter as 'A web question or instruction, including any ordinary webpage URLs,' so the description's mention of putting URLs in the prompt largely restates the schema. The description does not add new parameter-specific details beyond confirming the text-based nature, and the guidance about media inputs relates to sibling tools rather than the prompt parameter.

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 clearly states the tool uses Gemini with Google Search and URL Context for web research, and explicitly directs media/file inputs to sibling tools (video, audio, document, image), distinguishing it from them. The verb 'Use' is supported by the resource 'Gemini with Google Search and URL Context'.

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 explicitly instructs to put ordinary webpage URLs directly in the prompt and tells users to use video, audio, document, or image for typed media and file inputs, naming the alternatives. This provides clear guidance on when to use this tool versus its siblings.

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