Skip to main content
Glama

update-metadata-ui

Update Chrome Web Store listing metadata through automated UI interaction when API updates fail or as the primary method due to API deprecation.

Instructions

Update listing metadata via Chrome Web Store dashboard UI automation (Playwright). Use this when API metadata updates are not reflected, or as the primary metadata update method since the v1 API is deprecated.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemIdNoExtension item ID (defaults to CWS_ITEM_ID env var)
titleNoStore listing title
summaryNoStore listing short summary
descriptionNoStore listing long description
categoryNoCategory label as shown in dashboard UI
homepageUrlNoHomepage URL
supportUrlNoSupport URL
storeIconPathNoAbsolute path to 128x128 store icon image
accountIndexNoGoogle account index in dashboard URL (default: 0)
headlessNoRun browser headless (default: false)

Implementation Reference

  • The handler for the 'update-metadata-ui' tool, which uses Playwright to automate Chrome Web Store dashboard interactions.
    async ({
      itemId,
      title,
      summary,
      description,
      category,
      homepageUrl,
      supportUrl,
      storeIconPath,
      accountIndex,
      headless,
    }) => {
      try {
        const id = resolveItemId(itemId);
        const idx = accountIndex ?? 0;
        const dashboardUrl = `https://chromewebstore.google.com/u/${idx}/dashboard/${id}/edit`;
    
        const hasAnyField = [title, summary, description, category, homepageUrl, supportUrl, storeIconPath].some(
          (v) => typeof v === "string" && v.trim().length > 0
        );
        if (!hasAnyField) {
          throw new Error("No fields provided for UI update.");
        }
    
        const context = await chromium.launchPersistentContext(DASHBOARD_PROFILE_DIR, {
          channel: "chrome",
          headless: headless ?? false,
        });
    
        try {
          const page = context.pages()[0] || (await context.newPage());
          await page.goto(dashboardUrl, { waitUntil: "domcontentloaded", timeout: 90_000 });
          await page.waitForTimeout(2500);
    
          if (page.url().includes("accounts.google.com")) {
            throw new Error(
              `Not signed in to Chrome Web Store dashboard. Open once with headless=false and sign in. Profile dir: ${DASHBOARD_PROFILE_DIR}`
            );
          }
    
          if (title?.trim()) {
            await fillTextFieldByLabel(page, ["Title", "제목", "Name", "이름"], title.trim());
          }
          if (summary?.trim()) {
            await fillTextFieldByLabel(
              page,
              ["Summary", "Short description", "요약", "짧은 설명"],
              summary.trim()
            );
          }
          if (description?.trim()) {
            await fillTextFieldByLabel(page, ["Description", "설명"], description.trim());
          }
          if (homepageUrl?.trim()) {
            await fillTextFieldByLabel(page, ["Homepage", "홈페이지"], homepageUrl.trim());
          }
          if (supportUrl?.trim()) {
            await fillTextFieldByLabel(page, ["Support", "지원", "Help", "도움말"], supportUrl.trim());
          }
          if (storeIconPath?.trim()) {
            await uploadFileBySectionLabel(
              page,
              ["Store icon", "스토어 아이콘", "아이콘", "Icon"],
              storeIconPath.trim()
            );
          }
    
          if (category?.trim()) {
            const categoryCombo = page
              .getByRole("combobox", { name: /category|카테고리/i })
              .first();
            if ((await categoryCombo.count()) > 0) {
              await categoryCombo.click();
              const option = page.getByRole("option", { name: new RegExp(escapeRegExp(category), "i") }).first();
              if ((await option.count()) > 0) {
                await option.click();
              }
            }
          }
    
          await clickSaveButton(page);
    
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify(
                  {
                    ok: true,
                    mode: "dashboard-ui",
                    profileDir: DASHBOARD_PROFILE_DIR,
                    url: page.url(),
                  },
                  null,
                  2
                ),
              },
            ],
            isError: false,
          };
        } finally {
          await context.close();
  • src/index.ts:569-598 (registration)
    Registration of the 'update-metadata-ui' tool with its schema definition using Zod.
    server.tool(
      "update-metadata-ui",
      "Update listing metadata via Chrome Web Store dashboard UI automation (Playwright). Use this when API metadata updates are not reflected, or as the primary metadata update method since the v1 API is deprecated.",
      {
        itemId: z
          .string()
          .optional()
          .describe("Extension item ID (defaults to CWS_ITEM_ID env var)"),
        title: z.string().optional().describe("Store listing title"),
        summary: z.string().optional().describe("Store listing short summary"),
        description: z.string().optional().describe("Store listing long description"),
        category: z.string().optional().describe("Category label as shown in dashboard UI"),
        homepageUrl: z.string().optional().describe("Homepage URL"),
        supportUrl: z.string().optional().describe("Support URL"),
        storeIconPath: z
          .string()
          .optional()
          .describe("Absolute path to 128x128 store icon image"),
        accountIndex: z
          .number()
          .int()
          .min(0)
          .max(9)
          .optional()
          .describe("Google account index in dashboard URL (default: 0)"),
        headless: z
          .boolean()
          .optional()
          .describe("Run browser headless (default: false)"),
      },
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals this is a UI automation tool using Playwright, implying it performs browser-based interactions. However, it doesn't disclose important behavioral aspects like authentication requirements, potential side effects, error handling, or what happens when only some parameters are provided. The description adds some context but leaves significant gaps.

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 extremely concise - just two sentences that efficiently convey the tool's purpose and usage guidelines. Every word earns its place, with no wasted text. The structure is front-loaded with the core purpose followed by specific usage context.

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

Completeness3/5

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

Given the tool's complexity (UI automation with 10 parameters) and the absence of both annotations and an output schema, the description should provide more behavioral context. While it explains when to use the tool, it doesn't cover what the tool actually does during execution, what users should expect, or potential limitations. The description is incomplete for a tool of this complexity with no structured behavioral documentation.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 10 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description.

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 tool's purpose: 'Update listing metadata via Chrome Web Store dashboard UI automation (Playwright).' It specifies both the action ('update'), the resource ('listing metadata'), and the method ('Chrome Web Store dashboard UI automation'), distinguishing it from the sibling 'update-metadata' tool which likely uses a different approach.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool: 'Use this when API metadata updates are not reflected, or as the primary metadata update method since the v1 API is deprecated.' It clearly differentiates from API-based alternatives and explains the preferred context for usage.

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

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/mikusnuz/cws-mcp'

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