browser_network_requests

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real value by disclosing the output shape (one line per request, the field order, and that full detail includes headers, post data and response body) — important since there is no output schema. It does not say whether the request list resets on navigation or is capped, which is the main remaining behavioral unknown.

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?

A single dense sentence that front-loads the default behavior and then the n-triggered detail mode. Every clause carries information (field order, detail contents); the only cost is a slightly telegraphic style that takes a moment to parse.

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 correctly carries the return-format burden by spelling out the column layout and the detail-mode payload. For a three-optional-parameter read tool this is nearly sufficient; only lifecycle questions (persistence across navigations, list size limits) are unaddressed.

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 baseline would be 3, but the description goes beyond it by defining what 'one request in full' actually contains (headers, post data, response body) and by documenting the per-line format that #n refers to. It does not elaborate on 'filter' or 'failed', which the schema already covers adequately.

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 precisely what is returned: the page's network requests, one line each, with the exact column layout (#n METHOD STATUS type url size time). It is clearly distinct from siblings like browser_console_messages or browser_evaluate, though it never names those alternatives explicitly. The verb is implicit ('The page's requests') rather than stated as 'list network requests', but the resource and scope are unambiguous.

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?

Usage is only implied: an agent can infer it should call this when it needs to inspect network traffic, and that passing n drills into a single request. There is no explicit guidance on when to prefer this over browser_console_messages or browser_evaluate, nor any note about whether the list reflects only the current page/navigation. Adequate but with clear gaps.

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