Control Device

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds no behavioral context beyond the action description. It does not detail side effects, confirmation, or device response. With annotations, the bar is lower, but the description could still elaborate on behavior (e.g., command sent to device).

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, front-loaded with the main purpose, followed by concrete examples and a usage tip. No superfluous words; every sentence earns its place.

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?

While the description covers purpose, common capabilities, and precondition (get_device), it lacks information about return values (no output schema) and potential side effects (e.g., device state change delay). For a mutation tool, this leaves some gaps.

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% with descriptions. The description adds value by listing common capability IDs with their expected value types (boolean for onoff, number 0-1 for dim, etc.), which helps the agent construct valid values beyond the 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?

The description clearly states the action ('Control a device by setting a capability value') and the resource (device capability). Examples of common capabilities aid understanding, but it does not explicitly differentiate from sibling tools like set_mood or set_alarm, which also control device aspects.

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 advises to 'Use get_device first to see available capabilities and their current values', providing clear context for when this tool should be used. However, it does not mention when not to use it or alternatives among siblings.

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