Skip to main content
Glama
andytango
by andytango

query_selector

Extract element information from web pages using CSS selectors to locate and retrieve specific content during browser automation.

Instructions

Get information about an element matching a CSS selector

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selectorYesCSS selector for the element
tabIdNoTab ID to operate on (uses active tab if not specified)

Implementation Reference

  • Handler function that executes the query_selector tool: retrieves the page, queries for the CSS selector, checks if element exists, and if so, extracts tag name, truncated text content, all attributes, and bounding box coordinates.
    async ({ selector, tabId }) => {
      const pageResult = await getPageForOperation(tabId);
      if (!pageResult.success) {
        return handleResult(pageResult);
      }
    
      const page = pageResult.data;
    
      try {
        const element = await page.$(selector);
    
        if (!element) {
          return handleResult(ok({
            exists: false,
            selector,
          }));
        }
    
        const info = await element.evaluate((el) => {
          const rect = el.getBoundingClientRect();
          const attributes: Record<string, string> = {};
    
          for (let i = 0; i < el.attributes.length; i++) {
            const attr = el.attributes[i];
            if (attr) {
              attributes[attr.name] = attr.value;
            }
          }
    
          return {
            tagName: el.tagName.toLowerCase(),
            textContent: el.textContent?.slice(0, 1000) ?? '',
            attributes,
            boundingBox: {
              x: rect.x,
              y: rect.y,
              width: rect.width,
              height: rect.height,
            },
          };
        });
    
        return handleResult(ok({
          exists: true,
          selector,
          ...info,
        }));
      } catch (error) {
        return handleResult(err(normalizeError(error)));
      }
    }
  • Registration of the 'query_selector' tool on the MCP server within registerContentTools, including name, description, schema, and handler.
    server.tool(
      'query_selector',
      'Get information about an element matching a CSS selector',
      querySelectorSchema.shape,
      async ({ selector, tabId }) => {
        const pageResult = await getPageForOperation(tabId);
        if (!pageResult.success) {
          return handleResult(pageResult);
        }
    
        const page = pageResult.data;
    
        try {
          const element = await page.$(selector);
    
          if (!element) {
            return handleResult(ok({
              exists: false,
              selector,
            }));
          }
    
          const info = await element.evaluate((el) => {
            const rect = el.getBoundingClientRect();
            const attributes: Record<string, string> = {};
    
            for (let i = 0; i < el.attributes.length; i++) {
              const attr = el.attributes[i];
              if (attr) {
                attributes[attr.name] = attr.value;
              }
            }
    
            return {
              tagName: el.tagName.toLowerCase(),
              textContent: el.textContent?.slice(0, 1000) ?? '',
              attributes,
              boundingBox: {
                x: rect.x,
                y: rect.y,
                width: rect.width,
                height: rect.height,
              },
            };
          });
    
          return handleResult(ok({
            exists: true,
            selector,
            ...info,
          }));
        } catch (error) {
          return handleResult(err(normalizeError(error)));
        }
      }
    );
  • Zod input schema for query_selector tool defining required CSS selector and optional tabId.
    export const querySelectorSchema = z.object({
      selector: selectorSchema,
      tabId: tabIdSchema,
    });
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'Get information' but does not specify what type of information (e.g., text, attributes, position), whether it's read-only, potential errors (e.g., if selector not found), or interaction effects. This leaves significant gaps in understanding the tool's behavior.

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, clear sentence that efficiently conveys the core purpose without unnecessary words. It is front-loaded and appropriately sized, making it easy to parse and understand quickly.

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?

Given the complexity of interacting with web elements, the lack of annotations and output schema means the description should do more to explain behavior, return values, and error handling. It fails to provide sufficient context for effective use, especially compared to sibling tools in a browser automation context.

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%, with both parameters ('selector' and 'tabId') well-documented in the schema. The description adds no additional meaning beyond the schema, such as examples or constraints, so it meets the baseline for adequate but not enhanced parameter semantics.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Get information') and resource ('an element matching a CSS selector'), making it easy to understand what the tool does. However, it does not explicitly differentiate from sibling tools like 'get_content' or 'select', which might have overlapping functionality, preventing a perfect score.

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, such as 'get_content' for broader content retrieval or 'select' for element interaction. It lacks context about prerequisites, exclusions, or specific scenarios where this tool is preferred, leaving usage unclear.

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/andytango/puppeteer-mcp'

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