start_recording

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

With no annotations provided, the description carries the full disclosure burden and does well: it reveals side effects (captures desktop, produces a video file), scope of capture (all connected screens, primary by default), the single-active-session constraint, the return contract (session ID and output path), and the OS-level permission requirement. It does not cover failure modes (e.g., behavior when permission is missing or a recording is already active), which keeps it short of a 5.

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?

Five sentences, each carrying distinct information: purpose, scope/mechanism, concurrency constraint, return values, and permission prerequisite. The purpose is front-loaded, and there is zero redundancy or repetition of schema content.

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 6-parameter tool with no output schema and no annotations, the description covers the essentials an agent needs: what the tool does, its system requirements, the active-session limit, and the meaningful return values (session ID and output path). Edge behavior (errors when permission is denied or a recording is already active, whether the call blocks) is undisclosed, which is a minor gap given the absence of an output schema.

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%, so the baseline of 3 applies even though the tool description itself adds no parameter-level information. The schema descriptions are notably rich (defaults, enum tradeoffs, CRF mapping, cross-references to list_screen_devices, path-resolution rules), but that is credit to the schema, not the description under evaluation.

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 full macOS desktop to a video file') and differentiates itself from its siblings: starting contrast with stop_recording, and the recording/device focus contrasts with get_recording_status, list_recordings, and list_screen_devices. The scope detail ('Records all connected screens (by default the primary display)') and mechanism (FFmpeg avfoundation) make the tool's identity unambiguous.

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?

Provides clear invocation context: a concurrency precondition ('Only one recording can be active at a time') and a hard prerequisite ('Requires Screen Recording permission granted to this terminal app'). It does not explicitly name alternatives or state when-not-to-use conditions, but the single-active-recording constraint effectively tells an agent to check get_recording_status first, and the schema cross-references list_screen_devices.

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