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

With no annotations to rely on, the description fully discloses key behaviors: the MJPEG-to-H.264 remuxing, server-side file output under /recordings/, the auto-stop mechanism (maxDurationSec) to prevent disk overflow, and the single-recording-per-device constraint. This gives the agent a complete mental model of side effects and safety without needing annotations.

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 a compact paragraph of five sentences, each adding essential information without redundancy. It front-loads the primary purpose and then covers technical details, prerequisites, and constraints. Slightly dense but efficient; no wasted words.

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?

Given there is no output schema, the description explicitly states the return value (recordingId) and its intended usage (pass to ios_record_stop). It covers the required prerequisite (session start), parameter behavior (auto-stop), and a key constraint (single recording). Everything an agent needs to call the tool correctly is present.

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%, so the description only needs to add value beyond parameter labels. It reinforces the maxDurationSec auto-stop behavior and mentions defaults (300/600), but adds little else for fps or udid that the schema already explains. This meets the baseline 3 but does not exceed it.

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 action ('Start a screen recording'), the target resource ('on an iOS device'), and adds specificity by explaining it captures the MJPEG broadcast and remuxes to H.264 mp4. This distinguishes it from sibling tools like ios_performance_record_start and device_record_start, which have different recording purposes. The constraint 'Only one recording per device at a time' further clarifies its scope.

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?

It provides explicit prerequisites ('An iOS session must already be running (call ios_start_session first)') and explains the workflow ('Returns a recordingId to pass to ios_record_stop'). However, it does not explicitly contrast with alternative recording tools (e.g., ios_performance_record_start) or state when to prefer this over them, relying instead on the intrinsic 'screen recording' context.

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