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

Annotations only declare it is a non-read-only, destructive, closed-world write; the description adds the operational traits that matter: one active session in v1, a named already_recording error on the second attempt, a returned session_id that later calls depend on, and a documented Screen Recording permission requirement with an explicit permission_required failure rather than a silent no-op. That is exactly the kind of beyond-annotation context this dimension rewards.

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?

Four short sentences, front-loaded with the action, then lifecycle constraint, then return value, then permission behavior. No padding or redundancy with the schema.

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 mutation tool with no output schema, the description still discloses the key return value (session_id), the error surface (already_recording, permission_required), and the permission prerequisite. An agent has everything needed to call it correctly and interpret the result.

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 the nested target object already documents kind, region, window_id, and display_id, so the description does not need to re-explain them. It only gestures at the target kinds and adds no syntax or default guidance beyond the schema (fps, show_cursor, output_path defaults all live in the schema). Baseline 3 is appropriate.

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 ("Begins a screen recording") plus the capture backends (ScreenCaptureKit) and the three target kinds (display, window, region), which cleanly separates it from screen_record_status, screen_record_stop, and screenshot_capture. An agent knows exactly what this does without opening the schema.

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 states the single-session constraint and that a second start returns already_recording, which is a real when-not condition, and names the downstream tools (record_marker, screen_record_stop) that consume the session_id. It stops short of telling the agent to check screen_record_status first or what to do after a permission_required error, so it is clear but not fully complete routing guidance.

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