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

The description discloses several behavioral traits beyond the schema: per-step reporting of which locator worked, RECOVERED status, accessible name drift detection, state-change detection (button disabled, element hidden), and the unsupported handling for native/coordinate steps. It also explains the default stopOnFailure behavior ('the second failure usually explains the first'), which adds context to the parameter.

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 a single, information-dense paragraph that front-loads the core action and then details the reporting behavior. Every sentence adds meaningful information: what happens, what is reported, and what is excluded. No filler or repetition of schema content.

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 3 parameters, 100% schema coverage, and no output schema, the description is complete. It explains the input source (recordingId), the execution model (re-resolving locators), the output semantics (per-step reports), and the limitations (web-only, coordinate steps unsupported). An agent has everything needed to decide when to call it and what to expect.

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 already documents all three parameters. The description adds value by explaining the stopOnFailure default rationale ('the second failure usually explains the first') and by clarifying that recordingId comes from ios_actions_record_stop or ios_actions_recordings. It doesn't add syntax details for udid, but the schema already covers that.

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 verb ('Replay') and resource ('a stored recording against a device'), and explains the mechanism (re-resolving locators, performing the recorded action again). It clearly distinguishes itself from recording tools (ios_actions_record_start/stop) and from flow_recording_replay by focusing on per-step locator recovery and state drift reporting.

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 states when to use this tool (to replay a stored recording) and what to expect. It also provides an exclusion: 'Web steps only: native steps and steps recorded by coordinates come back unsupported rather than being replayed blind.' This tells the agent when NOT to expect full functionality and what alternative behavior to anticipate.

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