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

No annotations are provided, so the description carries the full burden. It discloses that the tool runs in the background, returns immediately with a replayId, auto-skips validation failures, and that resetAppData is destructive and erases app data. This is strong behavioral disclosure for a mutation tool, though it doesn't detail failure modes or what happens if the replay cannot start.

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 sentences with no filler. The core behavior and return value are front-loaded, the sibling alternative is named, and the validation-failure caveat is a single clause. Every sentence earns its place.

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 background-start tool with no output schema, the description covers the key things an agent needs: what it returns, how to poll, when to prefer it, and the destructive resetAppData caveat. It doesn't describe error conditions or how to abort, but those are covered by sibling tools (flow_replay_abort) and the description is otherwise complete for correct invocation.

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 context beyond the schema: it explains the purpose of resetAppData (clean first-run state for enrollment/first-run flows), notes it is destructive and Android-only, and clarifies that platform is auto-detected if omitted. This goes beyond the schema's field descriptions.

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 clearly states the tool kicks off a flow replay in the background, returns a replayId immediately, and explicitly distinguishes it from flow_recording_replay. The verb 'kick off' plus the resource 'flow replay' and the immediate-return behavior make the purpose unambiguous.

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 explicitly says to use this instead of flow_recording_replay when you want to monitor live or do other work while the replay runs, and tells the agent to pass the returned replayId to flow_replay_status for polling. It also notes validation failures are auto-skipped because MCP has no interactive input, which is a clear when-to-use/when-not-to-use signal.

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