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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false): it discloses the server-side remux, the /recordings/ output location, the auto-stop safety cap that prevents disk fill, the returned recordingId, and a concurrency limit of one recording per device. These are exactly the operational facts an agent needs before invoking a stateful start.

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 dense sentences, each carrying distinct information (what it does, how it works, prerequisite, safety cap, return value, concurrency), with the action front-loaded and no filler or repetition.

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?

With no output schema, the description compensates by naming the return value (recordingId) and its consumer (ios_record_stop); it also covers prerequisites, failure-prevention (auto-stop), and concurrency. Nothing an agent needs to call this correctly is missing.

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 the schema already documents udid, fps, and maxDurationSec with defaults and ranges. The description restates maxDurationSec's default/max but adds no syntax or semantics beyond the schema, so the 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?

States a specific verb+resource ('Start a screen recording on an iOS device') and then explains the actual capture pipeline (MJPEG broadcast remuxed server-side to H.264 mp4). An agent can distinguish it from ios_record_stop, ios_record_cleanup, ios_actions_record_start, and device_record_start without opening a 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?

Gives a concrete prerequisite ('An iOS session must already be running (call ios_start_session first)') and routes the agent forward to ios_record_stop via the returned recordingId. It also flags the single-recording-per-device constraint, but never contrasts itself with the other record-start siblings (ios_actions_record_start, ios_performance_record_start), leaving that choice to inference.

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