start_recording

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

With no annotations provided, the description carries full burden and excels: it discloses immediate capture behavior (no warmup), platform-specific formats, the max 180s limit on Android, the single-recording-at-a-time constraint, the 5-minute auto-stop, and the auto-stop trigger on stop_app. This is exceptionally transparent for a stateful recording tool.

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, every one adds distinct value: capture timing, platform formats, concurrency limit, auto-stop conditions. No redundancy, front-loaded with the operational verb and immediate-usage guidance.

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-optional-param tool with no output schema, the description is nearly complete. It covers formats per platform, duration limits, concurrency, and lifecycle interactions with stop_app. Minor gap: doesn't state what the return value is (e.g., the file path or recording ID), though no output schema exists to convey this.

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 coverage is 100% for the single save_path parameter, which is already fully described as an optional absolute path with temp-directory fallback. The description adds no parameter-specific detail beyond the schema, so baseline 3 applies.

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 verb+resource ('Starts recording the screen of the running app's device') and distinguishes from siblings like screenshot and stop_recording. It specifies immediate capture with no warmup delay, which is critical behavioral detail for agent selection.

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 on platform support (iOS Simulators, macOS Desktop, Android), the single-recording constraint, and auto-stop conditions. It doesn't explicitly name sibling alternatives (e.g., stop_recording) when to use them instead, but the context is sufficient for typical selection decisions.

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