cdp_navigateNavigate an attached browser tab to a URL and wait for its load event, so you can reliably continue with page interactions or checks.
Navigate the attached page to a URL and wait for the load event.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to load in the attached tab | |
| port | No | CDP debug port (default 9222). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this is a mutating action. The description adds genuinely useful timing context ('wait for the load event'), telling the agent the call blocks until load completes. It stops short of stating that the current page state is discarded or what happens on timeout/failed load.
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?
A single front-loaded sentence with no filler, and the blocking/load-wait behavior is stated inline rather than buried. It is arguably too terse for a mutating navigation tool, but nothing in it is waste.
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?
There is no output schema, so return values needn't be explained, and annotations cover the safety profile. Still, for a destructive navigation primitive in a crowded set of cdp_* tools, the agent gets no hint about preconditions (attachment), failure/timeout behavior, or how this differs from cdp_launch/cdp_new.
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%, with both url and port documented inline including a default, so the schema does the heavy lifting. The description mentions the URL target but adds no syntax constraints (schemes allowed, relative vs absolute) beyond what the schema already provides.
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?
Names a specific verb (navigate) and resource (the attached page) plus the target input (a URL), so the action is unambiguous. It does not, however, distinguish itself from adjacent CDP siblings such as cdp_launch, cdp_new, or cdp_switch, which also change what page is loaded or shown.
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?
There is no guidance on when to use this instead of cdp_launch (start a browser), cdp_new (open a tab), or cdp_switch (change active target). The word 'attached' hints that a target must already be attached, but that prerequisite is never stated as a condition for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.