gemini_query

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

No annotations exist, so description must disclose behavioral traits. It reveals Google Search grounding and the AI Overviews proxy nature, which is key behavioral insight beyond a simple query. However, details like idempotency, rate limits, or default model behavior are omitted.

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?

Two sentences concisely cover purpose, grounding, and the unique value proposition. Front-loaded with the main action, and no fluff.

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 3 parameters and an output schema, the description only addresses the required 'question' parameter. The optional parameters are undocumented, leaving gaps for effective use. The output schema likely covers return values, but the description could hint at optional params.

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%, yet the description only mentions 'a question' and ignores the optional 'model' and 'system_prompt' parameters. No parameter details are provided, failing to compensate for the schema gap.

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 asks Gemini with Google Search grounding a question and returns answer with cited URLs. It specifies the verb 'Ask', the resource 'Gemini (with Google Search grounding)', and distinguishes from sibling tools like claude_query and openai_query by highlighting the AI Overviews proxy use case.

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 implies use when seeking grounded Gemini answers or AI Overview insights but lacks explicit when-not to use or alternative suggestions. Sibling tools cover other LLMs, so context is provided, but no direct guidance on choosing this over others.

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