Watch network requests

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

No annotations exist, so the description carries the transparency burden. It discloses that only metadata is indexed, that no response body is read/stored, and that restricted-category origins never enter the index. This covers the key safety- and privacy-relevant behaviors. It does not mention whether the watch persists across navigations or how to stop it, but the disclosed traits are substantial.

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?

Five sentences, each earning its place: purpose, exclusions, behavioral constraints, prerequisite, and optional parameters. The key purpose is front-loaded and clarifies scope immediately. Slightly longer than the terse 2-sentence examples but not padded.

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?

This is a moderately complex tool with no output schema or annotations. The description explains the intended lifecycle, captures safety behavior, and names the prerequisite (cdp_attach). It doesn't describe its return value or how to stop/clear the index, but the core invocation rules and constraints are present and sufficient for correct use.

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%, and the description adds no new parameter-level semantics beyond what the schema already provides. The description repeats that optional patterns narrow URLs but does not add format details, defaults, or interaction rules; thus 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 the specific verb ('Enable the Network domain') and the resource ('an attached tab') and states it keeps an in-memory index of metadata. It also explicitly says 'No response body is read or stored', which distinguishes it immediately from cdp_response_body and cdp_network_requests.

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 states 'Requires cdp_attach' and explains optional patterns narrow indexing, but does not explicitly say 'use cdp_network_requests to retrieve this index' or 'do not use when you need response bodies'. Since the sibling tools make the relationship inferable, this is clear context without full alternatives.

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