start_screen_recording

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

Annotations show non-read-only, non-destructive, non-idempotent. The description adds that recording runs in a background thread, only one at a time, and the return format includes path, fps, and status. This adds behavioral context beyond what annotations provide.

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: two sentences plus structured Args/Returns. Every sentence carries essential information, and the important constraint (single recording) is front-loaded.

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?

Given the tool's complexity and the presence of output schema, the description covers all key aspects: purpose, single-recording constraint, companion tool, background execution, and parameter summary. No missing critical information.

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 0% (the tool description does not repeat schema details), but the schema itself has detailed descriptions for each parameter. The tool description just lists parameter names and marks some as optional, which adds minimal value over the schema.

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 action: 'Begin recording the screen to an mp4 file in a background thread.' It specifies the resource (screen), the output format (mp4), and provides enough context to distinguish it from siblings like stop_screen_recording and 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 explicitly says 'Only one recording can run at a time' and directs to call stop_screen_recording to finish. This gives clear usage context and the companion tool, though it does not describe alternatives for similar actions.

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