Gemini Chat

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

No annotations are provided, so the description carries the full burden. It discloses critical behavioral traits: grounding by default, the max_tokens cap behavior (not consumption), the fact that values below 4096 are ignored, and that temperature is ignored on Gemini 3+ (forced to 1.0). It also explains the thinking_level parameter's scope and defaults. This is exemplary transparency for a complex tool.

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 front-loaded with the core purpose and then dives into critical warnings. It is dense but not bloated; every sentence adds value. The only minor issue is that the max_tokens warning is repeated in both the description and the schema parameter description, which is slightly redundant but reinforces the critical point. Overall, it's well-structured and efficient.

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?

Given the tool's complexity (7 parameters, 1 required, 100% schema coverage, output schema present), the description is remarkably complete. It covers model selection, grounding, token budget behavior, temperature quirks, thinking levels, and timeout recommendations. The output schema exists, so return values don't need explanation. This is a model example of a complete tool description.

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%, but the description adds significant value beyond the schema. For max_tokens, it explains the cap-vs-consumption distinction, the 4096 threshold, and clamping behavior. For temperature, it notes the forced 1.0 on Gemini 3+. For thinking_level, it clarifies which models support which values. The description enriches every parameter with practical context.

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's purpose: 'Chat with Google Gemini models.' It specifies the default model (gemini-3.1-pro-preview) and grounding behavior, distinguishing it from sibling tools like gemini_deep_research or gemini_prompt_assistant. The verb 'chat' plus the resource 'Google Gemini models' is specific and unambiguous.

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 provides explicit usage guidance: it warns against setting max_tokens, explains the server's automatic allocation, and clarifies that small values cause thinking tokens to burn the budget and return empty output. It also includes a recommended timeout (300000 ms) and the schema details valid model options and exclusions (e.g., 'Do NOT pass gemini-1.5-* or gemini-pro'). This is comprehensive and actionable.

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