live_start_run

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 the immediate return with a runId, the asynchronous nature, failure behavior when a run is already active, and the requirement for a connected side panel. It could mention side effects on run history more explicitly, but the core behavior is transparent.

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 dense but not verbose. Each sentence serves a distinct purpose: main action, polling guidance, and failure/prerequisite conditions. No irrelevant detail is included.

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?

Given there is no output schema, the description sufficiently explains what the caller receives (a runId), how to track progress, how to handle a busy tab, and what environment is required. It provides enough context 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?

The schema covers 60% of parameters. flowId and params lack descriptions, though their purposes are fairly inferable. The project, dataset, and session parameters are well explained, including default behavior and when session is needed.

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 verb 'Starts a flow running live' and identifies the resource (a flow on the side panel's target tab). It also distinguishes this tool from live_replay_flow by noting it returns immediately instead of waiting.

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 contrasts with live_replay_flow, directs the user to poll live_get_run or live_list_runs, mentions the one-run-per-tab constraint, and points to live_cancel_run for freeing a busy tab. It also states the prerequisite that the side panel must be open and connected.

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