watch_camera

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

Discloses behavior like collecting frames over duration, scene change detection, keyframe selection, optional audio transcription, and JSON return. No annotations exist, so the description carries the full burden; it does well but could mention if any data is persisted or discarded.

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?

Efficient: a one-line summary, then two constraint lines, then bulletized args and returns. No redundant sentences, well-structured.

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?

Covers key aspects: streaming duration, scene detection, audio, and return format. With no output schema provided in input, the description's return note helps. Could add edge cases like what happens if phone disconnects.

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?

Input schema has 0% description coverage, so the description fully compensates by explaining each parameter (duration_seconds, include_audio, max_frames) with defaults and purpose.

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 tool streams camera frames with scene detection and optional audio, and the verb 'stream' plus resource 'camera' distinguishes it from siblings like capture_camera (still image) and watch_screen (screen).

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 mentions it's only available in personal mode and requires prior connection via show_pairing_qr(), providing clear context. However, it doesn't explicitly state when not to use it or suggest alternatives, so there's room for improvement.

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