collect

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 does disclose that the run is 'bounded' and that the returned run_id is 'durable', implying asynchronous background execution. However, it omits side effects such as browser launch, network activity, data persistence, or how to follow up on the run.

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?

A single, tight sentence communicates the action and primary output immediately with no filler. Every word earns its place.

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 tool with 14 parameters, no schema descriptions, and no annotations, this one-sentence description is insufficient. It does not explain what 'bounded' means, how to choose platform/mode, or how the run relates to sibling status/result/logs tools. The presence of an output schema helps return-value expectations, but invocation knowledge remains incomplete.

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 input schema has 14 parameters with 0% description coverage, and the description adds no parameter-level meaning. Required parameters like platform and mode are completely unexplained, and meaningful defaults such as login_type, browser_mode, and timeout_minutes are left to inference.

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 action ('Start'), a clear resource ('collection run'), and the key output ('durable run_id'). This clearly distinguishes it from sibling tools like stop, status, result, and logs, which manage or inspect runs rather than initiate them.

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?

No guidance is given on when to use this tool versus alternatives such as preview, export, or runs. The only context is the verb 'Start', so usage timing and selection criteria must be inferred by the agent.

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