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

Annotations only indicate false hints; the description adds real behavioral context by stating that a detached process is spawned, logs are written to the session's raw log, and shorter hang events are dropped at stop time per `minHangMs`. It does not enumerate cleanup or failure behavior, but it goes beyond the structured hints.

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 compact, front-loaded with purpose, and organized with Parameters and Returns sections. It avoids fluff and every sentence adds operational value for selecting and calling the tool.

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, the description correctly documents the return fields (`sessionId`, pid, guidance) and the follow-up tool. It covers the core invocation workflow, though it omits details such as session cleanup, concurrency, and what happens if no booted simulator is available.

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 0%, so the description must carry parameter meaning, and it does: `udid` defaults to booted, `predicate` overrides the os_log predicate, and `minHangMs` defaults to 250 and controls the filtering threshold at stop time. This is meaningful and more than the bare schema types.

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 uses a precise verb-resource pairing: 'Begin a HangBuster capture session' and explains the concrete mechanism (spawns a detached `simctl log stream` filtered to hang/stall/watchdog/jetsam events). It also mentions the paired `hang-stop` tool, which distinguishes it from sibling simctl and idb tools.

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 lays out a clear workflow: start capture, reproduce the hang, then call `hang-stop` to parse/cluster/rank. This gives the agent an explicit usage sequence, though it does not explicitly state when alternatives like `simctl-stream-logs` or `hang-list` should be preferred.

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