network_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 well by explaining that bodies are only captured when capture_bodies=true, restricting capture to json/text/xml/form, capping size at body_limit bytes, and routing the user to network_get_detail for inspection. It could additionally mention whether starting a capture clears previous logs or whether the capture persists across navigations, but the core behavior is transparent.

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: the first sentence states the action, and the second covers the optional behavior, output access, and a helpful alternative comparison. Every sentence contributes information without redundancy or padding.

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?

Given no output schema and no annotations, the description supplies the key details needed to invoke the tool successfully: what it starts, how to enable richer capture, the body size limit, and how to inspect results. Minor gaps exist around stopping capture and whether prior capture state is reset, but these are secondary to a correct first call.

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 the schema already documents both parameters. The description adds value beyond the schema by tying capture_bodies to the additional recording of headers and text bodies and by clarifying that body_limit applies as a byte cap to each body. This enriches parameter understanding rather than merely repeating the schema.

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 opens with a specific verb and resource: 'Start capturing network requests.' It distinguishes itself from related siblings by naming network_get_detail as the way to inspect captured payloads, so an agent can tell this is the capture-starting tool rather than a retrieval or interception tool.

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 on when to use capture_bodies=true and points to network_get_detail as the companion tool. It also explicitly steers away from evaluate()+fetch(). It doesn't spell out exclusions such as when to prefer intercept_start or http_request, but the primary usage scenario is clear.

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