start_screen_recording

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

The annotation readOnlyHint=false already indicates a write operation, but the description adds behavioral details: recording happens in a background thread, the single-recording constraint, and that the file is flushed upon stop. These are informative beyond the structured metadata and help the agent understand side effects.

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?

The description is extremely concise and well-structured: purpose in the first line, key usage constraint in the second, and a compact args/returns section. Every sentence is purposeful and no redundant content exists, making it easy to parse quickly.

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 tool that starts an asynchronous recording, the description covers the key operational aspects: the background thread, the one-at-a-time limit, the need to call stop_screen_recording, and the return JSON structure. With an output schema present, detailed return values need not be repeated, and the description is sufficiently complete for an agent to invoke and manage the recording.

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?

The description lists the parameter group ('fps, monitor, optional region and output path') but the schema already contains detailed descriptions for every property (e.g., fps 'Frames per second to capture', output_path auto-generation). The description adds minimal semantic value beyond the schema, which carries the full explanatory load.

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 'Begin recording the screen to an mp4 file in a background thread', specifying the exact action and resource. It is easily distinguished from sibling tools like screenshot (single capture) and stop_screen_recording (stops recording), preventing confusion.

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 provides clear context: 'Only one recording can run at a time' and instructs to call stop_screen_recording to finish. This gives practical guidance on when to use the tool and how to properly end a session, though it does not explicitly mention alternatives like screenshot for still captures.

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