Start Screen Recording

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

Annotations only declare non-read-only and non-destructive, so the description adds genuine behavioral substance: the recording persists in the background after the call returns and requires a companion stop call, and it discloses the return value (the save path). This meaningfully extends what an agent could infer from annotations alone, with no contradiction.

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?

Three sentences, each earning its place: purpose, background-run behavior, and return value. The core action is front-loaded with zero filler or redundancy.

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 explicit mention of the returned save path is valuable, and the recording lifecycle is fully explained. The only minor gap is that the description's lifecycle narrative omits the timeLimit auto-stop behavior, though the input schema documents it.

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 schema already documents each parameter well, including the .mp4 filename requirement for output and the cross-reference to mobile_list_available_devices for device discovery. The description adds no parameter-level detail but does not need to, so the baseline 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?

The description states a specific verb plus resource: 'Start recording the screen of a mobile device.' It distinguishes itself from its natural sibling mobile_stop_screen_recording by naming that tool explicitly, and 'recording' is semantically distinct from the sibling screenshot tools (mobile_take_screenshot, mobile_save_screenshot).

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 description frames the workflow clearly: the recording runs in the background until stopped with mobile_stop_screen_recording, alerting the agent that this is a stateful two-call operation and that a follow-up call is required. It does not, however, give explicit when-not guidance against the screenshot tools for still captures, leaving that distinction implied.

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