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

The description discloses key behavioral traits beyond the schema: steps execute in order, locators are used with coordinate fallback, validation failures are auto-skipped so replay never blocks, and a full result summary with per-step pass/fail is returned. With no annotations provided, this is strong behavioral disclosure for a replay tool.

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 redundancy. The core action, execution mechanism, return value, and non-blocking behavior are all covered efficiently. Front-loaded with the primary verb and resource.

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 replay tool with no output schema, the description covers the execution model, return summary, and failure handling. It does not detail the exact structure of the result summary or mention cancellation/abort options, but the essential information for invoking it correctly is present.

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%, so the schema already documents all five parameters. The description adds context for validateElements (failures auto-skipped) and mentions recordingId comes from flow_recording_list, but it does not add significant meaning beyond the schema for the other parameters. Baseline 3 is appropriate.

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 replays a flow recording on a device, executes recorded steps in order using element locators with coordinate fallback, and returns a per-step pass/fail summary. This distinguishes it from related siblings like flow_replay_start, flow_recording_list, and flow_replay_summary by focusing on the replay execution itself.

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 implies usage context: replay a previously recorded flow on a device, with recordingId sourced from flow_recording_list. It does not explicitly state when to prefer this over flow_replay_start or ios_actions_replay, but the clear scope and reference to flow_recording_list provide adequate context for an agent to select it.

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