Close all active browser sessions gracefully, then force kill any that remain. Use this to clean up Chrome browsers and directories after automation tasks.
Gracefully close all active browser sessions (tries to close browsers properly first, then force kill if needed)
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Skip graceful close and immediately force kill all processes and clean directories |
Changes observed during successful MCP inspections.
v1.3.8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses the two-phase close (graceful first, force-kill fallback), which is real behavioral context. However, it omits what actually gets destroyed, whether session data/directories are cleaned, permission requirements, and return behavior, which matters for a destructive process-killing tool.
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; the core action and the fallback behavior are stated compactly. Every clause earns its place.
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 destructive, no-annotation mutation tool with no output schema, the graceful/force behavior is covered but the blast radius is not: it doesn't say what data is removed, whether directories are cleaned, or what the result looks like. Adequate but incomplete for its risk profile.
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?
The single 'force' param is fully documented in the schema (100% coverage), so the baseline is 3. The description adds modest value by explaining the default non-force path ('tries to close properly first'), which contextualizes what force=true skips, but adds no syntax or format detail beyond the schema.
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 ('close') plus resource ('all active browser sessions'), and the 'all' scope cleanly distinguishes it from the sibling close_browser and from cleanup_sessions. An agent can tell what it does and that it targets every session, not one.
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?
No explicit when-to-use, when-not-to-use, or alternative routing (e.g. close_browser for a single session, cleanup_sessions for leftovers). Usage is only implied by the tool name; the description offers no selection guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.