Skip to main content
Glama
pvinis
by pvinis

playwright_close

Shut down the browser and free up resources in the Playwright MCP Server, ensuring efficient management of browser sessions during web interactions.

Instructions

Close the browser and release all resources

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Primary execution logic for 'playwright_close' tool: special case that closes the browser instance if it exists, handles errors, resets global browser state, and returns appropriate success message.
    if (name === "playwright_close") {
      if (browser) {
        try {
          if (browser.isConnected()) {
            await browser
              .close()
              .catch((e) => console.error("Error closing browser:", e));
          }
        } catch (error) {
          console.error("Error during browser close in handler:", error);
        } finally {
          resetBrowserState();
        }
        return {
          content: [
            {
              type: "text",
              text: "Browser closed successfully",
            },
          ],
          isError: false,
        };
      }
      return {
        content: [
          {
            type: "text",
            text: "No browser instance to close",
          },
        ],
        isError: false,
      };
    }
  • Tool definition including name, description, and empty input schema (no parameters required). Part of createToolDefinitions() for MCP registration.
    {
      name: "playwright_close",
      description: "Close the browser and release all resources",
      inputSchema: {
        type: "object",
        properties: {},
        required: [],
      },
    },
  • Class-based handler implementation for closing browser (CloseBrowserTool.execute). Similar logic to inline handler but not invoked due to early return in toolHandler.ts.
    export class CloseBrowserTool extends BrowserToolBase {
      /**
       * Execute the close browser tool
       */
      async execute(args: any, context: ToolContext): Promise<ToolResponse> {
        if (context.browser) {
          try {
            // Check if browser is still connected
            if (context.browser.isConnected()) {
              await context.browser.close().catch(error => {
                console.error("Error while closing browser:", error);
              });
            } else {
              console.error("Browser already disconnected, cleaning up state");
            }
          } catch (error) {
            console.error("Error during browser close operation:", error);
            // Continue with resetting state even if close fails
          } finally {
            // Always reset the global browser and page references
            resetBrowserState();
          }
          
          return createSuccessResponse("Browser closed successfully");
        }
        
        return createSuccessResponse("No browser instance to close");
      }
    }
  • Dispatch registration in handleToolCall switch statement (redundant due to special case above).
    case "playwright_close":
      return await closeBrowserTool.execute(args, context);
  • Inclusion in BROWSER_TOOLS array, used to determine browser launch requirements.
    "playwright_close",
Behavior2/5

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

With no annotations provided, the description carries full burden but only states the basic action. It misses behavioral details like whether this is destructive (likely yes, but not confirmed), if it requires an active browser session, or potential side effects (e.g., releasing resources).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It is front-loaded with the core action and resource, making it immediately understandable without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations or output schema, the description is insufficient. It lacks context on prerequisites (e.g., must have an open browser), consequences (e.g., irreversible closure), or what happens post-execution (e.g., session state).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema coverage, so no parameter documentation is needed. The description appropriately omits parameter details, earning a high baseline score for not adding unnecessary information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Close') and the resource ('the browser'), distinguishing it from sibling tools like playwright_navigate or playwright_get. It precisely communicates the tool's function without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives (e.g., end_codegen_session for session termination) or prerequisites (e.g., after completing browser operations). It lacks context for appropriate invocation timing.

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

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pvinis/mcp-playwright-stealth'

If you have feedback or need assistance with the MCP directory API, please join our Discord server