List watched network requests

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

With no annotations, the description carries the full burden, and it delivers: 'in-memory' signals ephemerality, 'Rows are metadata only' sets expectations about data richness, and the explicit exclusions prevent the agent from assuming headers or bodies are present. It does not cover failure modes or whether an active watch is required, but the disclosed traits are genuinely useful beyond the schema.

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 short sentences totaling roughly 27 words, with the primary action front-loaded and the exclusions following logically. Every sentence earns its place; there is no filler or repetition of the title.

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 simple one-parameter list tool, the core behavior and data boundaries are well covered. The main gap is that with no output schema, the description does not specify which metadata fields each row contains (URL, status, timing), leaving the agent to guess at the row structure.

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 100% — sessionTabId is fully documented as 'Claimed tab session id returned by claim_tab.' The description adds nothing about the parameter itself, but the schema is doing the heavy lifting, so the baseline of 3 is appropriate.

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 names a specific verb ('Return'), resource ('in-memory network request index'), and scope ('for an attached tab'), which is further reinforced by the title 'List watched network requests'. The explicit exclusions ('Response headers, Set-Cookie, and request post data are never included') delineate it from cdp_response_body, so an agent can distinguish it from siblings without opening any 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?

The description provides clear context: use it to retrieve the metadata-level network request index for an attached tab. The 'never included' phrasing acts as a when-not boundary (do not use if you need headers, cookies, or post data), but it does not explicitly name an alternative tool like cdp_response_body or note the prerequisite of cdp_network_watch.

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