start_video_stream

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

The description discloses that it opens a viewer window (ffplay) and auto-starts a scrcpy session, which adds useful behavioral context. However, annotations already cover readOnlyHint=false and destructiveHint=false, and the description doesn't mention cleanup behavior, port conflicts, or how the stream is stopped—though the sibling stop_video_stream tool hints at that. The annotation non-read-only nature aligns with starting a stream.

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 sentences, zero waste. Every clause adds value: it names the protocol (HTTP MJPEG), the effect (viewer window), and the dependency handling (scrcpy auto-start). Highly concise and front-loaded with the core purpose.

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 an output schema present and good annotations, the description carries a reasonable burden. It explains the stream mechanism, the viewer, and dependency behavior. It doesn't mention how to terminate the stream, but the sibling stop_video_stream covers that, and the output schema likely documents the stream URL. This is adequate for a tool of this complexity.

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%, so both port and serial are already documented in the schema. The description adds minimal value beyond the schema—it doesn't explain what the serial selects or how port interacts with the stream endpoint. Per the baseline rule for >80% coverage, a 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?

The description clearly states the verb+resource (start an HTTP MJPEG video stream of the device screen) and mentions it opens a viewer window via ffplay. It also notes it starts a scrcpy session if needed. It distinguishes from sibling stop_video_stream and screen_record_start by framing this as a live HTTP MJPEG stream rather than a recording, though it doesn't explicitly contrast with screen_record_start.

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 implies when to use (viewing live screen remotely via HTTP MJPEG) but doesn't explicitly state when not to use it or give alternatives like screenshot or screen_record_start/stop for capturing frames. The mention of auto-starting scrcpy is a useful context cue, but there's no exclusion or alternative guidance.

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