List handles for controlled Edge IE mode windows and optionally read each window's URL and title; restoring the original top-level window resets frame context and references.
List handles. With include_details=true, visit each controlled window to read its URL/title, then restore the original window at top level. This resets frame context and references. Handle order is not creation order.
| Name | Required | Description | Default |
|---|---|---|---|
| include_details | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that detail mode visits every window, resets frame context and references, and restores the original window at top level — a significant side effect an agent must know. It also warns handle order is not creation order. It stops short of saying whether the call is otherwise side-effect free or how many windows it may visit.
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?
Four short sentences, front-loaded with the core action and the side-effect warning immediately after. "List handles" is slightly too terse to stand alone, but nothing is wasted.
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 tool with no annotations and no output schema, the description covers side effects and the flag well, but leaves the return value undescribed — the agent cannot tell whether it gets a raw handle list, handle/title/URL tuples, or an ordering guarantee beyond the negative warning.
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 0% for the single boolean, so the description must compensate and largely does: it states what include_details=true does (visit each window and read URL/title) and implies the default is a bare handle list. It does not describe the shape of the returned entries under either mode.
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?
"List handles" combined with the tool name browser_windows makes the resource inferable, and the mention of "each controlled window" confirms it enumerates browser windows. However it never states plainly that it lists window handles, and it does not distinguish itself from siblings like browser_sessions or browser_status.
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?
It explains the conditional behavior of include_details ("With include_details=true, visit each controlled window..."), which implies when to set it. But there is no explicit when-to-use guidance versus browser_sessions, browser_status, or browser_switch_window, and no stated exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.