kia_stop_climate

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

Discloses the two-phase execution (preview vs actual), polling mechanism for airCtrl, separation of commandAccepted and stateConfirmed, and observed delay. Adds substantial context beyond annotations.

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?

Concise at ~80 words, front-loaded with purpose. Somewhat dense with technical details but no wasted sentences.

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 all parameters, return fields (commandAccepted, stateConfirmed, ign3), polling logic, and timing. Adequate given no output schema.

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 coverage is 100%, but description adds practical context: vinKey is vehicleKey, confirm must be true, waitSeconds default/max/observed. Extra value beyond schema.

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?

Clearly states 'Stop remote climate control' with specific endpoint and live-verified status. Unambiguous verb-resource pairing and distinguishable from sibling 'kia_start_climate'.

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?

Explains the critical confirm:true requirement and the dry-run behavior without it. Includes observed timings but lacks explicit when-to-use guidance versus alternatives beyond start/stop.

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