repro

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

Descriptors go beyond annotations: discloses buffer clearing, waiting for async events, returning both browser and console/network data plus per-step results and errors. No contradiction with readOnlyHint and openWorldHint.

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?

Single sentence packed with key information: buffer clearing, action types, event waiting, return contents. No redundant phrases; every part contributes to understanding.

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 complexity (9 params, nested objects, no output schema), description covers main behavior and return structure. Missing details on idleMs, waitFor, timeoutMs etc., but schema fills those. Sufficient for agent to decide when to use.

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 description adds context by explaining the high-level flow (clear, single action vs sequence, event waiting). Reinforces clear parameter behavior and the action/actions choice. Adds moderate value beyond schema.

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?

Description clearly states it's a one-shot reproduce-and-correlate tool: clears buffer, performs action(s), waits for async events, returns full logs, per-step results, and errors. Distinguishes from sibling browser_* tools by emphasizing aggregation and correlation.

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?

Explicitly recommends using sequences for multi-step flows like 'navigate → click → type → click submit'. Implicitly suggests alternatives: single actions can use browser_* tools, but this provides correlation. Lacks explicit when-not-to-use but context is clear.

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