Poll Raw CDP events

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It warns that results may contain secrets or private browsing data, which is a critical transparency element. It also clearly states the lack of field sanitization, but does not mention pagination behavior or whether polling is incremental. Overall, it provides valuable context beyond the bare schema.

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 concise sentences, with the first stating the core function and the second providing a critical safety caveat. Every word earns its place, and it is front-loaded with the main action. No unnecessary details are 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 the lack of annotations, output schema, and parameter descriptions, the description is incomplete. It does not explain the return format, how polling works (e.g., cursor semantics), or that sessionId is required. The tool has four parameters, and the description offers no guidance on how to use them or what to expect in response, leaving significant gaps for an AI agent.

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 by explaining parameters, but it does not. The parameter names are somewhat self-explanatory (limit, timeoutMs), but 'afterCursor' and the required 'sessionId' are not explained in context. The description adds no parameter-level information, making it difficult for an agent to understand how to correctly set these fields.

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 tool reads original CDP event methods, source targets, and params without field sanitization, specifying both the verb and resource. The phrase 'without field sanitization' differentiates it from sanitized alternatives like browser_watch_events. This is a specific and unambiguous purpose.

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 implies usage for accessing raw CDP events, but it does not explicitly state when to use this tool over siblings like browser_watch_events or browser_network_poll. It also does not mention exclusions or prerequisites beyond the required sessionId in the schema. The guidance is inferred rather than explicit.

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