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

Annotations only give generic hints (idempotent, non-destructive, open world); the description adds real behavioral substance: the remote-activation flow, the full state machine (off/requested/live/paused/away/ended), the paused_by_worker signal, and the token cost formula. Nothing here repeats structured fields.

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-loaded with the purpose, then mechanics, then states, then cost — a sensible ordering. Every sentence carries information, though the states enumeration and cost paragraph make it longer than strictly minimal; still no filler or repetition.

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 description compensates by naming the observable signals an agent will receive (paused_by_worker, state transitions) and the two tools that consume the resulting stream. An agent has everything needed to invoke it correctly and interpret what follows.

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%, so baseline is 3, but the description adds genuine meaning the schema lacks: the token economics tying frame_size and frame_every_seconds to cost (768px ≈ 440 tokens, 30s/30min ≈ 27k) and the practical guidance to 'ask for what the task needs'. That is decision-relevant information beyond the raw ranges.

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 ('Ask the worker to go live on an interactive task') and immediately clarifies the crucial mechanic that distinguishes it from a camera-control tool: the worker must tap Go live. It is clearly separable from siblings like capture_frame, await_interactive_events, and stop_interactive.

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 routes to companions ('instruct with send_chat_message', 'Follow along with await_interactive_events') and states the effect of re-invocation ('Calling it again just changes the cadence or size'). It also gives a hard prohibition ('never use them to identify or look up people') and the resume constraint (only the worker can resume).

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