alexa_speak

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

Goes well beyond the annotations by disclosing the side effect's reach ('Everyone in the room hears it, so it cannot be taken back'), which explains why destructiveHint=true matters here. It also documents the confirmation gate, the phase-1 'confirmation-required' preview, and how confirmToken must be handled (never on first call, never reused).

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 core action and the destructive consequence before the procedural confirmation details. Four sentences, no filler, though the final sentence is dense and partially restates the confirmToken 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?

With no output schema, the description supplies the missing return-path context itself: the confirmation prompt, the preview plus confirmToken, and the repeat-call contract. An agent has everything needed to invoke this destructive, open-world tool safely.

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 structured fields already carry the constraints; the description nonetheless adds real meaning, notably that 'speak' takes exactly one device while 'announce' takes one or more, and that the confirmToken is only for clients without elicitation. Slight overlap with the schema's own confirmToken description keeps it from a 5.

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 concrete verb and resource ('Make Alexa say something out loud') and immediately decomposes it into the two real behaviors: 'speak' (one device, Alexa's voice) and 'announce' (one or more devices, chime first). That distinction is not derivable from the name alone and cleanly separates it from siblings like alexa_playback or alexa_run_routine.

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 clear mode-selection criteria (single device vs multi-device broadcast) and spells out the precondition that confirmation must come first, including the two-step fallback path. It does not name sibling tools as alternatives, but the when-to-use context is otherwise unambiguous.

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