live_replay_flow

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

With no annotations, the description carries the burden and discloses key behavioral facts: it uses the user's real session/login and targets a specific tab (pinned tab or active tab). It also states the requirement for an open connected side panel. It doesn't mention side effects like whether a run record is created, but for a replay action the core behavior is clear.

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 two sentences with no redundancy. It front-loads the core action, then provides crucial environment and target details. Every clause adds value (live, side panel, real session, tab targeting) without unnecessary elaboration.

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?

The description covers the essential context: what it does, where it does it, and preconditions (side panel connected, tab targeting). It does not mention return values or errors, but since there is no output schema and the action is straightforward replay, this is sufficient for a live interaction tool.

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 60%, leaving flowId and params undocumented. The tool description mentions 'a single flow' which implies flowId but does not clarify the 'params' object or how it relates to flow execution. There is no additional explanation of the session parameter in the description, though the target tab behavior hints at session usage. Overall, the description does not compensate for the missing parameter documentation.

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 action ('Replay a single flow live') and specifies the environment (side panel's connected browser tab, real chrome.debugger, user's real session). It distinguishes this from sibling tools like live_replay_scenario or live_run_step by explicitly saying 'single flow' and 'live'.

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?

It provides a prerequisite ('requires the side panel open and connected to this project') and explains the target tab selection logic. However, it does not explicitly mention alternative tools like live_replay_scenario for scenarios or live_run_step for individual steps, so guidance on when not to use this tool is implicit rather than explicit.

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