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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, and the description usefully adds that queued utterances are discarded and that an admin-issued api_key is required. However, discarding pending speech reads as mildly at odds with destructiveHint=false, and no behavior is described for the no-op case (e.g. when nothing is speaking).

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?

Two short sentences with the primary action front-loaded and no filler. The api_key parenthetical is arguably redundant with the required-parameters list, keeping it just short of ideal brevity.

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 simple two-parameter mutating tool with no output schema this is nearly adequate, but it omits the session_id explanation, error/no-op behavior, and any routing versus end_session, leaving real gaps the structured fields do not fill.

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 only 50%: api_key is documented in the schema while session_id has no description anywhere. The description partially compensates by stating api_key is required and where to obtain it (admin panel), but it adds nothing about session_id.

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 states a specific action pair — stop the currently playing utterance and discard queued utterances — which is more precise than the title "中断する". It implicitly distinguishes itself from siblings like end_session (session survives, only speech stops) but never names or contrasts with them.

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?

There is no explicit when-to-use guidance and no comparison to the obvious alternative, end_session, which also halts activity. The agent must infer that interrupt is a lightweight, session-preserving stop while end_session tears the session down.

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