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

Annotations declare it is not read-only, not destructive, not idempotent, so the safety profile is covered. The description adds useful behavioral context beyond that: it tells the agent the call yields an id and the captured commands/events/errors, which matters because there is no 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?

A single front-loaded sentence with the action first and the return payload second; no filler. Slight loss because 'across both channels' is vague and adds little.

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 one-parameter stop tool with no output schema, the description covers what the tool does, its safety via annotations, and its return shape. It stops short of explaining what happens to the finalized recording (persistence, where to read it), which would fully close the loop.

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?

Only one parameter (udid) with 100% schema description coverage, so the schema already fully documents it. The description's 'for a device' merely restates this; the baseline of 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 (Stop) and resource (action recording) plus the return payload (id and captured commands/events/errors). It implicitly contrasts with ios_actions_record_start, but never names or distinguishes itself from siblings like ios_actions_record_status or ios_actions_recording_read.

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?

'Stop the action recording' implies the lifecycle context (invoke after a recording has been started), so usage is inferable. However, there is no explicit when-to-use/when-not guidance and no reference to alternatives such as status or read tools.

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