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

Annotations only cover the generic safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true); the description adds far more: reboot preserves data, a 10-minute throttle, an at-most-once guarantee for unconfirmed reboots, and what it means when the call returns while the phone is still creating or starting. That is exactly the behavioral context annotations cannot express.

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-loaded with the purpose and no filler sentences, but the middle clause ("a reboot the phone service didn't confirm is never sent twice") is dense and awkward, and the trailing get_phone/start_phone remark is somewhat crammed in.

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 carries the return semantics itself: it explains the possible still-creating/starting end state and the correct follow-up call. Rate limit, idempotency behavior, and next steps are all covered, so an agent has enough to call and recover correctly.

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 100% and the only parameter (phone_id) is documented in the schema with its format and source. The description adds no syntax or format detail beyond that, so the baseline 3 is appropriate.

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?

Specific verb+resource with scope: "Restart a phone that is stuck, keeping everything on it, and wait until it is ready again." It also distinguishes itself from siblings by naming get_phone and start_phone, so an agent can route without opening their 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-to-use context and rate limit ("once every 10 minutes"), plus a clear alternative for follow-up ("wait for ready with get_phone instead") and a contrast against start_phone ("would renew the session"). Nothing about choosing this tool is left to inference.

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