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

Annotations declare non-read-only, non-idempotent, non-destructive, but the description adds genuinely non-obvious behavioral detail: it sends SIGTERM to the remux pipeline specifically so the mp4 gets a valid moov atom. That explains the shutdown semantics beyond what annotations convey, though it says nothing about failure modes or repeat-call behavior.

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?

Three tight sentences, front-loaded with the operation and its prerequisite, followed by the mechanism and the return fields. No filler.

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, listing the returned fields (hostPath, sizeBytes, durationMs, codec) is valuable and closes the biggest gap; annotations cover safety. It stops short of describing error behavior for invalid or already-stopped recordingIds, which would make it fully complete.

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% — recordingId is already documented as "recordingId returned by ios_record_start" — so the schema carries the full burden. The description only indirectly reinforces this via the ios_record_start reference and adds no format or syntax detail beyond the schema.

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 names a specific verb (Stop) and resource (an iOS screen recording) and ties it directly to its counterpart ios_record_start, which lets an agent distinguish it from the many other stop/record siblings (ios_actions_record_stop, ios_performance_record_stop, device_record_stop).

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 establishes the precondition clearly — the recording must have been started by ios_record_start — which is the main context an agent needs. It does not, however, mention alternatives or edge cases such as calling it without an active recording, or when to use ios_record_cleanup instead.

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