browser_capture_network

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: capture is buffered, 'start' resets fresh, 'stop' merely pauses, and everything runs through the page's PerformanceObserver. It omits important traits such as buffer size limits, whether the buffer survives navigation, and what entry fields are returned.

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 purpose sentence is front-loaded and the Args block is well structured with one line per parameter. It is tight overall, though the Args list format is somewhat mechanical rather than prose-optimized.

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 three-parameter tool with no output schema and no annotations, the description covers the operation modes, filtering, and tab targeting adequately. It stops short of describing the shape of the returned buffer entries, which the agent would need to consume the results.

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 fully compensate, and it does: all three parameters are explained, including every op value, the millisecond semantics of 'since' ('startTime >= since'), and that tab_id is optional and defaults to the active tab.

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?

States a specific verb and resource ('Capture network requests') and names the underlying mechanism (PerformanceObserver), so the agent knows exactly what is being observed. It does not, however, distinguish itself from nearby siblings like browser_intercept or browser_wait_for_network_idle, leaving overlap for the agent to resolve.

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 op modes ('start' captures fresh, 'stop' pauses, 'read' returns the buffer) implicitly tell the agent how to drive the tool, and 'read' being the default is helpful. There is no explicit guidance on when to prefer this over browser_intercept or browser_wait_for_network_idle, so usage versus alternatives is only implied.

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