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

Goes well beyond the annotations: it discloses that apps, files and sign-ins are preserved across a restart, that calling on a running phone renews the session with a new deadline and reserved credit, and that the tool may return while the phone is still creating/starting. These are non-obvious state and timing behaviors that the readOnlyHint/idempotentHint flags alone could not 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 primary action and outcome in the first two sentences, then adds the async/routing caveat. The final sentence is long and slightly dense with nested clauses, but each clause carries actionable meaning.

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?

There is no output schema, so the description correctly carries the burden of explaining return semantics (may return before "ready") and the follow-up path. Combined with the annotated safety profile and fully documented schema, an agent has everything needed to invoke this 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%, with idle_timeout and max_duration fully documented in the schema (including the 15-second last_active_at cadence and ranges). The description adds no parameter-level detail beyond referring to "its ID" in the routing sentence, so the baseline of 3 applies.

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 and resource ('Start a parked phone') plus the blocking behavior ('wait until it is ready'), and describes a second mode (session renewal on an already-running phone). An agent can clearly distinguish this from park_phone, get_phone, or reboot_phone without opening any 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?

Explicitly tells the agent what to do when the call returns before the phone is ready: call get_phone with its ID and wait for "ready", and explains why (get_phone only reads, while start_phone would renew the session). This is a concrete when-to-use-this-vs-sibling rule, not an implication.

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