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

No annotations are provided, so the description carries the burden. It discloses that it's a paired start/stop workflow requiring a subsequent stop call and that it records over time (implying resource duration). It doesn't disclose resource cost, whether multiple concurrent recordings are allowed, or impact on device performance. Adequate but not rich.

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?

Two sentences, both substantive. The first sentence front-loads purpose and the stop-pairing workflow. Efficient with no filler, though slightly dense with the 'screen recording' analogy packed in.

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 start-recording tool with no output schema and no annotations, the description provides the critical pairing detail (call stop with returned sessionId) and the bundleId behavioral difference. Reasonably complete for a simple parameter set, though it could note what the session tracks beyond CPU/memory and any sampling limits.

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 documents all 3 parameters. The description adds the bundleId semantics ('focus one app; else top processes by CPU') which enriches that parameter's meaning. It doesn't add detail on intervalMs beyond the schema's default of 1000. Baseline 3 with slight value-add.

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?

Clear verb+resource: start recording CPU/memory over time. The screen-recording analogy and 'top processes by CPU' fallback add useful scope. It doesn't explicitly distinguish from sibling ios_performance_snapshot or the similar android_performance_record_start, but the iOS prefix and recording-vs-snapshot distinction is reasonably clear.

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?

Explicitly says to 'Drive the app, then call ios_performance_record_stop with the returned sessionId' and explains that focusing with bundleId records one app, else top processes. This gives clear usage context and workflow sequencing, though it doesn't state when NOT to use it vs the snapshot tool.

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