start_recording

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

Annotations already declare this is a non-readonly, non-destructive, non-open-world operation, so the mutation profile is covered. The description adds the concrete output location (~/Videos/Recordings/), which is genuinely useful context, but says nothing about what happens if a recording is already in progress, session duration, or how the file is finalized.

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?

One sentence, front-loaded with the action and followed by the storage location; there is no filler. Every clause carries information an agent needs.

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 single-parameter, no-output-schema tool this is close to sufficient, but a recording tool needs the stop/finalize path and already-recording behavior to be callable correctly end-to-end. Those gaps keep it at a minimum-viable level.

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% and there is only one optional parameter, so the schema already documents 'audio (default false)'. The description does not mention audio capture at all, leaving the default behavior for sound to be read from the schema alone — acceptable, but no added meaning.

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 ('Start recording the screen') and names the artifact type and destination ('video file in ~/Videos/Recordings/'), which implicitly separates it from the sibling start_recording_gif. It does not explicitly name that sibling or contrast with stop_recording/is_recording, so sibling differentiation is inferential rather than stated.

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?

Usage is implied by the name and by the presence of start_recording_gif, stop_recording, and is_recording in the sibling list, but the description never says when to call this vs. the gif variant or that stop_recording must be called to finalize. The agent must infer the full lifecycle.

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