set_temperature

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the mutation profile is covered. The description adds valuable beyond-annotation context: it does not turn power on, only one confirmed target is affected, and 'Accepted is not physically ready' warns of eventual consistency between acknowledgement and physical change. It does not discuss reversibility or permission requirements.

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 tight sentences with zero waste. The primary action and scope are front-loaded, followed by invocation forms, then the two behavioral caveats.

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?

For a destructive, no-output-schema mutation tool whose annotations cover safety, the description supplies enough to call it correctly: value ranges, unit rules, mode exclusivity, and the acceptance-vs-physical-readiness caveat. Remaining gap is how 'target' must be identified and confirmed before calling.

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%, so the description must carry the parameter burden, and it largely does: F range 55–115 integer, C range 13–48 in 0.5 steps, enumerated mode values maximum_cooling/maximum_heating, and mutual exclusivity of mode vs value/unit. The 'target' parameter is only described as a 'confirmed target' with no format or confirmation mechanism, leaving one 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?

States a specific verb and resource ('Change ... temperature') with a scope constraint ('only one confirmed target') and explicitly differentiates from the power path ('Does not turn power on'). An agent can tell this apart from set_power without opening either schema.

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?

Gives explicit invocation shapes: value+unit for a numeric setpoint, or an 'explicitly requested' maximum_cooling/maximum_heating mode with no value/unit. Also states the exclusion that it does not power the device on. It stops short of naming which sibling to call when the user actually wants power or mode changes outside these two modes.

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