kia_start_charge

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

Beyond annotations, it reveals that without confirm:true it's a dry-run preview, describes timing (~30-60s for batteryCharge to go true), and clarifies that the tool accepts requests even when not plugged in but no action occurs.

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 sentences each adding distinct value: action, verification, prerequisite, and dry-run behavior. No filler, well-organized.

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?

Covers prerequisites, behavior, verification method, and confirmation nuance. Without an output schema, it provides enough info on expected state changes and how to confirm success.

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 already covers all three parameters with descriptions (100% coverage). The description adds context about the confirm flag's behavior and chargeRatio's default, but schema is already strong.

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 'start charging' with specific verb and resource, mentions underlying API endpoint, and clearly differentiates from siblings like kia_stop_charge or kia_set_charge_limits.

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 states that the car must be plugged in, warns that an unplugged car accepts the request but does nothing, recommends confirming with kia_vehicle_status, and explains the confirm:true parameter's role in making a network call.

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