Observed network requests

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

Annotations only declare readOnlyHint=true, and the description corroborates that with 'observes rather than intercepts' while adding genuinely new behavioral facts: the 500-event in-memory buffer, newest-first retention, and the per-connection lifetime ('since this server connected'). It does not say what happens on rollover or whether events survive navigation, which keeps it from a 5.

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?

Three sentences, front-loaded with the scope constraint and closing with the buffer limit, with no filler. The middle sentence is dense with event names but each one earns its place by defining what the method filter accepts.

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?

With no output schema, the description carries the burden of describing return shape, and it does so via the enumerated event types and the newest-first 500-event buffer. A caller still has to infer the exact field layout of each event, which is the one remaining gap for a read-only observation tool.

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% with only two optional parameters, so the schema already documents limit and method fully. The description does supply the event-name vocabulary that a caller would pass to method (beforeRequestSent, responseCompleted, fetchError), which is marginal value beyond the schema's example.

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 ('Report network activity'), enumerates the three event types it captures, and explicitly distinguishes itself from the sibling browser_network_intercept ('observes rather than intercepts'). An agent can separate it from the interception tools without opening the schema.

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?

'Use it to find out what a page actually loaded' gives a clear context for invocation, and the observe-vs-intercept contrast implicitly routes interception needs to browser_network_intercept. It stops short of explicitly naming that sibling or stating a when-not condition, so it is strong but not complete routing guidance.

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