Start or stop intercepting requests

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

Annotations already flag destructiveHint=true, but the description adds the crucial non-obvious consequence: matching requests are HELD and pages can appear to hang if nothing continues them. That is a genuine behavioral disclosure beyond structured metadata, and it directly justifies the destructive annotation.

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?

Front-loads the action, then the hang warning, then the remedy and the related tool. The warning icon and parenthetical protocol details are slightly verbose but every sentence carries actionable content.

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?

Covers the stateful-toggle risk and recovery path thoroughly, which is the main thing an agent needs. The remaining gap is scope: it never says whether interception applies globally, per tab, or per context — a real ambiguity given the absence of any tab/context parameter.

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 urlPattern description in the schema is unusually thorough (escaping, parse-as-URL requirement), so the description need not repeat it. The description adds no parameter-level meaning of its own beyond mentioning the interception phase, so the baseline 3 applies.

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?

States a specific verb pair (turn on/off) plus the exact resource (BiDi request interception) and even names the protocol commands (network.addIntercept / removeIntercept, phase beforeRequestSent). It is immediately distinguishable from siblings like browser_network_continue_all and browser_network_requests, which it references by name.

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?

Gives explicit when-to-use conditions and the required companions: pair with browser_network_continue_all or browser_network_provide_response, and turn interception OFF when finished. It also tells the agent where the resulting data shows up (browser_network_requests), leaving nothing to inference.

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