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

Annotations declare a non-readonly, non-destructive, non-idempotent mutation, but the description adds crucial operational context: it reuses the shared device control session, remuxes H.264/H.265 server-side, avoids on-device storage and FLAG_SECURE limits, auto-stops to prevent disk fill, and allows only one recording per device. These are traits an agent cannot infer from annotations or schema.

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?

Despite its length, every sentence carries non-redundant information: session reuse, remux pipeline, storage guarantees, auto-stop rationale, return value, and concurrency limit. The purpose is front-loaded and the detail is warranted for a stateful recording start tool.

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?

No output schema exists, but the description states the return value (recordingId) and its use with device_record_stop. Annotations cover safety hints, and the description covers behavior, constraints, and cleanup semantics, leaving no significant gap for correct invocation.

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%, so both udid and maxDurationSec are documented. The description reinforces the maxDurationSec auto-stop behavior and default/max values, but adds little parameter-specific syntax or meaning beyond the schema's own descriptions.

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+resource ('Start a screen recording on an Android device') and distinguishes this from the iOS sibling by platform and from on-device recording by its server-side remux architecture. The agent can identify it as the Android screen-recording start tool 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?

States the platform (Android) and the action (start screen recording), and routes the agent to device_record_stop via the returned recordingId. It also notes the single-recording-per-device constraint. However, it never explicitly contrasts with sibling recording tools such as android_performance_record_start or ios_record_start, nor states when not to record.

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