page_network_start

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

With no annotations, the description carries the behavioral burden. It discloses that capture happens below the page, is invisible to page JS, is unpatchable, and that captcha/API answer data travels through it. It does not mention side effects, whether repeated starts reset capture, or how recording ends, but the disclosed traits are meaningful and non-obvious.

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 compact and front-loaded with a clear protocol-level capture label. The two explanatory sentences add important context without padding. Minor redundancy between 'PROTOCOL-LEVEL NETWORK CAPTURE' and 'BELOW the page' keeps it from a 5.

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 explains what, why, and when to start, but it omits how to stop or retrieve the recorded data, and does not address the optional filter parameter. Given there is no output schema and no annotations, an agent would still need to infer the full capture workflow from sibling tool names.

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 only 33%: session_id and page_id have no descriptions in the schema, and the tool description does not explain their meaning or relationship. The description only generically refers to 'this page' without mapping it to page_id. The optional filter is documented in the schema but not reconciled with the claim of recording 'every HTTP response.'

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 ('start recording') and resource ('every HTTP response for this page'), and explains the protocol-level scope ('BELOW the page, invisible to page JS, unpatchable'). This clearly distinguishes it from sibling network-read tools and other page operations.

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?

It gives a clear timing instruction: 'Start before triggering the flow you want to see.' This tells the agent when to invoke the tool relative to other actions. It does not explicitly name alternatives or say when not to use it, 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.