alexa_set_thermostat

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

Adds substantial behavior beyond the annotations: it reads the thermostat first, refuses out-of-range setpoints, defaults units to the device scale, and requires user confirmation via either elicitation or a preview+confirmToken two-step flow. This is exactly the kind of interaction semantics annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) cannot convey, and nothing conflicts with them.

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?

One dense, front-loaded paragraph ordered by importance: what it does, then per-mode parameter rules, then safety behavior, then confirmation. Every clause is load-bearing; it is slightly long for a single block but has no filler 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?

For a 7-parameter mutation tool with no output schema, it covers the mutation model, unit defaults, validation/refusal behavior, and the full two-phase confirmation contract including token handling. Nothing an agent needs to invoke it correctly, including the easy-to-mishandle confirmToken, is left unstated.

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 the description still adds real semantic value the schema does not: in AUTO the omitted bound is retained from the current setting, and HEAT/COOL consume the single temperature rather than the bounds. That clause alone raises it above the baseline-3 case for fully documented schemas.

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+resource ('Set an Alexa-connected thermostat') and enumerates exactly what is controllable: setpoint (heat-to/cool-to) and mode. An agent can distinguish this from sibling all-purpose tools like alexa_control_smart_home 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 mode-conditional usage rules ('in AUTO mode pass lower/upper', 'in HEAT or COOL mode pass temperature') and explains the confirmation prerequisite. It stops short of naming alternative tools or stating when not to use this one versus alexa_control_smart_home, so it is clear context rather than full routing guidance.

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