network_capture_start

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does this well by noting the capture is 'bounded', that the tab is not foregrounded, and that a debugger lease is released on stop. It could be more explicit about failure modes or what happens if a capture is already active, but the key side effects are disclosed.

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 filler. It front-loads the main action and capture scope, then gives the essential lifecycle instruction in the second sentence.

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 clearly covers the core workflow and there is an output schema to describe return values, but with 6 optional parameters and zero schema descriptions, an agent still lacks guidance on how to tune the capture. The 'bounded' framing is vague about which limits apply, and no failure semantics are mentioned.

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 for the 6 undocumented parameters. It only hints at one parameter group, 'optionally response bodies' for include_bodies, and 'bounded' loosely suggests timeout/max_entries, but timeout, session_id, body_timeout, max_body_bytes, and max_entries are left unaddressed.

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 verb and resource: 'Start bounded CDP Network capture on a real-browser tab.' It also clarifies what is captured ('requests, responses, and optionally response bodies') and explicitly contrasts with the sibling stop tool by naming network_capture_stop.

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 gives clear context for when this tool is appropriate: capturing network traffic on a real-browser tab, and it explains the necessary follow-up call to network_capture_stop to retrieve the buffer and release the debugger lease. It does not explicitly discuss exclusions or compare against alternatives like console_capture_start or cdp_command, so it stops short of a 5.

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