Navigate a specific browser tab to an HTTP(S) URL by tab_id, or create a new tab for the URL only when new_tab is true.
Navigate an explicit tab or create one only with new_tab=true. No hidden observe.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute HTTP(S) URL without embedded credentials. | |
| tab_id | No | Exact stable tab_id; no implicit tab selection. | |
| new_tab | No | ||
| timeout | No | Phase timeout in milliseconds (10000; download 120000). |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'No hidden observe' is a genuine behavioral disclosure (navigation does not implicitly observe), but it omits what navigation actually does, whether it waits for load, and what state results. Partial disclosure only.
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?
Two short sentences, zero filler, and the core constraint is front-loaded. Every clause carries weight.
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 navigation/mutation tool with no annotations and no output schema, the description leaves gaps: no mention of what happens to the current tab state, waiting/timeout behavior, or whether content is returned. Adequate but thin given the tool's complexity.
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 75%, with url, tab_id, and timeout already documented. The description reinforces the new_tab semantics ('create one only with new_tab=true'), which the schema encodes only structurally via oneOf, but adds little beyond the schema's own constraint language.
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 (navigate) and resource (a tab), plus the create path conditioned on new_tab=true. It partially differentiates from the observe sibling via 'No hidden observe', though the phrasing is terse and assumes familiarity with the observe/act/goto trio.
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 clause 'create one only with new_tab=true' implies when the create path applies, and 'No hidden observe' hints at a contrast with observe. However, no explicit when-to-use vs alternatives (observe, act, list_tabs) is given, leaving selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.