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

No annotations are provided, so the description carries the behavioral disclosure burden. It does this well by explaining the recording lifecycle, the need to call the stop sibling, and the default 'top processes' behavior. It could be more explicit about side effects like whether only one recording can run at a time, but the essentials are covered.

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 with no filler. The core action is front-loaded, followed by the workflow and parameter behavior. Every sentence contributes useful information.

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 one required parameter and no output schema, the description covers the necessary steps and the stop callback. It could be slightly more explicit about the start call's own return value, but 'the returned sessionId' makes this reasonably clear.

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 baseline is 3. The description adds meaningful semantics beyond the schema by explaining that bundleId focuses recording on one app and that omitting it records top processes by CPU, and by referencing the sessionId needed for the stop call.

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 states a specific action — 'Start recording per-process CPU/memory over time' — with a clear resource and scope. It also distinguishes this tool from its paired sibling ios_performance_record_stop and nearby ios_performance_snapshot by framing it as the start of a time-series workflow.

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?

The description gives a clear workflow: start recording, drive the app, then call the stop tool with the returned sessionId. It also explains the optional bundleId behavior and the fallback to top processes, but it doesn't explicitly discuss when to prefer ios_performance_snapshot or mention exclusions.

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