flow.replay_to_checkpoint

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

With no structured annotations, the description carries the behavioral disclosure burden. It does include [approval required], [device mutation], and [risk:dangerous] tags, which flag danger and side effects. Still, it does not detail what auto-advancing actually does to the device, whether it can be reversed, or what side effects might occur beyond the broad mutation warning.

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 efficient sentence with the risk and mutation warnings front-loaded. It contains no filler, but it is so brief that it sacrifices substantial parameter and behavior detail.

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?

This is a dangerous mutation tool with seven parameters and no output schema, yet the description provides almost no operational context. It does not explain what the tool returns, how dryRun alters behavior, what delayMs/minimumScore control, or what failure modes exist. The description is too thin for the tool's complexity.

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 0%, so the description must compensate for the seven undocumented parameters. It only maps 'requested checkpoint' to a likely parameter (targetCheckpointId) and implicitly maps 'session' to sessionId. No meaning is added for dryRun, delayMs, testName, serverUrl, minimumScore, or targetCheckpointId beyond raw names.

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 ('Auto-advance'), a specific resource ('an Appium session'), and a precise trigger condition ('from a previously seen screen to the latest or requested checkpoint'). This clearly distinguishes it from siblings like flow.record_checkpoint and flow.plan_replay.

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 phrase 'from a previously seen screen' implies the tool should be used after a checkpoint has been recorded, and 'latest or requested checkpoint' suggests replay scenarios. However, it never explicitly states when to use this tool versus alternatives like flow.plan_replay or manual Appium navigation steps, and offers no exclusions.

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