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

No annotations are provided, so the description carries the full burden of disclosure. It richly discloses behavior: subscribes to shared control session (no duplicate process), server-side remux into mp4 on server host, no on-device storage, no FLAG_SECURE limits, no 180s cap, auto-stop prevents indefinite disk fill. This is thorough, though it doesn't mention return format details for recordingId (partially mitigated by the unnamed output 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?

The description is 6 sentences and dense with useful details, but every sentence earns its place: purpose, session behavior, codec/container details, limitations (no on-device storage/FLAG_SECURE/180s), auto-stop, return value, concurrency constraint. No wasted words or redundancy.

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 recording-start tool with no output schema, the description covers the essential behavioral contract well: what it returns (recordingId), when it stops, concurrency limits, storage implications, and relation to device_record_stop. It's slightly lengthy but comprehensive. The only minor gap is not detailing what happens to the mp4 file after recording (retention/location), though this may be outside the tool's scope.

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 have descriptions. The description adds meaningful context beyond the schema by explaining the default (300) and max (600) in text, and clarifying that omitting maxDurationSec uses the default auto-stop cap. The description also adds the 'one recording per device' constraint. It doesn't describe formats or formats beyond schema, but the schema is already clear.

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 tool starts a screen recording on an Android device, with a specific verb (start) and resource (screen recording). It distinguishes itself from siblings like device_record_stop and android_performance_record_start by explicitly mentioning the mp4 remuxing, no FLAG_SECURE limitation, and the distinct companion stop tool. This differentiation is helpful given the large sibling list.

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 explains the auto-stop behavior (maxDurationSec default 300, max 600), states 'Only one recording per device at a time', and references the companion device_record_stop for the recordingId. It also clarifies it subscribes to the shared device control session without creating a duplicate process, helping agents avoid redundant setup.

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