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

Annotations already cover the safety profile (not read-only, not idempotent, not destructive, closed-world), so the description's burden is lighter. It usefully adds that stop returns an MP4 file with the recording, but says nothing about what happens on a redundant start, whether the recording is tied to the session, or how long it persists.

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 operation stated first and the payoff of 'stop' second; nothing is wasted. The 'Cloud iPhone:' prefix is slightly redundant with the title but sets platform context in one phrase.

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 two-state toggle tool with no output schema, the description covers the essential contract: start/stop and that stop yields the MP4. It leaves the session-dependency and repeat-start behavior unexplained, which an agent would want before invoking.

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% and every parameter has a description, including defaults for device and session_id and the request_key replay idiom, so the schema carries the parameter burden. The description adds no format or default detail beyond it, which is the baseline 3 case.

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: start or stop a video of the Simulator's screen on a cloud iPhone. It's clearly distinct from the Mac-side siblings and from snapshot-style tools like phone_ui_look, though it never names an alternative directly.

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?

The clause 'to show a person what happened' implies the intent (capture evidence for a human), and the start/stop pairing is implicit in the action enum. But there is no explicit when-to-use versus screenshotting or phone_ui_look, and no stated prerequisites such as needing a running phone.

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