alexa_set_device_mode

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

Annotations only say non-readonly, non-destructive, idempotent, open-world; the description goes well beyond by disclosing the two-phase confirmation behavior: a client-side confirmation prompt where supported, otherwise a preview response carrying a confirmToken that must be echoed on a repeat call. It also clarifies the token must never be invented or reused, which is exactly the kind of behavioral detail annotations cannot convey.

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?

Front-loads the what and the examples, then the alternative tool, then the confirmation caveat - a sensible ordering. It is dense and slightly long, but nearly every clause carries operational weight (the confirmToken sentence is partly redundant with the schema description).

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 mutation tool with no output schema and an unusual two-call confirmation path, the description supplies everything an agent needs: valid value sources, sibling routing, and the exact token round-trip contract. Nothing material is missing.

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%, so the baseline is 3, but the description adds real meaning: `setting` disambiguates which mode control when a device has several, and `mode` accepts a name or an id as surfaced by alexa_list_device_modes. The confirmToken lifecycle is also explained beyond the schema's warning text.

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 (change a mode setting on an Alexa smart-home device) and immediately enumerates concrete instances: thermostat fan mode, robot vacuum mode, light effect. It also names the siblings it is NOT (alexa_garage_door, and implicitly alexa_list_device_modes for value lookup), so an agent can separate it from alexa_control_smart_home or alexa_set_thermostat without opening schemas.

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?

Explicit when (changing a mode-type setting), explicit when-not (garage doors - go to alexa_garage_door), and names the dependency tool for valid values (alexa_list_device_modes). The guidance is actionable and leaves nothing to inference about routing.

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