Start network monitoring

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It states that the monitor is metadata-only, never returns headers or bodies, and that rawSessionId exists to avoid a second debugger attachment. These are important, non-obvious behaviors. It does not describe the return format or the event queueing lifecycle, which would be useful, but the most critical constraints are disclosed.

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 three short sentences, each adding distinct value: the core purpose, the rawSessionId reuse tip, and the metadata-only limitation. It is front-loaded with the primary action and avoids repetition or filler.

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 tool with 7 parameters, no annotations, and no output schema, the description covers the core nature (metadata-only, tab-scoped) but omits details about the filtering/limit parameters and the workflow with network_poll/network_stop. It is adequate for understanding the tool's role but not complete for effective use of all parameters.

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 compensate for explaining parameters. It only implicitly explains tabId ('tab-scoped') and rawSessionId ('reuse that Raw CDP attachment'). The other parameters (urlMode, maxBytes, maxEvents, urlIncludes, resourceTypes) are not mentioned at all, leaving their purpose and effects unclear. The description does not add meaning to the majority of 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 uses a specific verb and resource: 'Start a tab-scoped, metadata-only Chrome network monitor.' It clearly distinguishes itself from network_poll and network_stop by focusing on the start action, and the 'metadata-only' limitation sets it apart from tools that capture bodies. The scope (tab-scoped) is also explicit.

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 provides a concrete usage guideline: 'Pass rawSessionId to reuse that Raw CDP attachment instead of attaching a second debugger.' It implies when to use this tool (start monitoring) versus the siblings (poll/stop) through the start/stop/poll workflow. However, it does not explicitly state when not to use it or name alternative tools for filtering or event handling.

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