Skip to main content
Glama

runAuditMode

Optimize web applications for SEO, accessibility, and performance by running comprehensive browser audits to identify and address improvement areas.

Instructions

Run audit mode to optimize our application for SEO, accessibility and performance

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • This is the registration of the 'runAuditMode' MCP tool. The handler function returns a fixed text content that provides instructions for the AI to enter 'Audit Mode' and sequentially call other audit tools: runAccessibilityAudit, runPerformanceAudit, runBestPracticesAudit, runSEOAudit, and optionally runNextJSAudit if the app uses NextJS. It outlines the process of analysis, planning changes, approval, implementation, and iteration.
    server.tool(
      "runAuditMode",
      "Run audit mode to optimize our application for SEO, accessibility and performance",
      async () => ({
        content: [
          {
            type: "text",
            text: `
          I want you to enter "Audit Mode". Use the following MCP tools one after the other in this exact sequence:
          
          1. runAccessibilityAudit
          2. runPerformanceAudit
          3. runBestPracticesAudit
          4. runSEOAudit
          5. runNextJSAudit (only if our application is ACTUALLY using NextJS)
    
          After running all of these tools, return back a comprehensive analysis of the audit results.
    
          Do NOT use runNextJSAudit tool unless you see that our application is ACTUALLY using NextJS.
    
          DO NOT use the takeScreenshot tool EVER during audit mode. ONLY use it if I specifically ask you to take a screenshot of something.
    
          DO NOT check console or network logs to get started - your main priority is to run the audits in the sequence defined above.
          
          After returning an in-depth analysis, scan through my code and identify various files/parts of my codebase that we want to modify/improve based on the results of our audits.
    
          After identifying what changes may be needed, do NOT make the actual changes. Instead, return back a comprehensive, step-by-step plan to address all of these changes and ask for approval to execute this plan. If feedback is received, make a new plan and ask for approval again. If approved, execute the ENTIRE plan and after all phases/steps are complete, re-run the auditing tools in the same 4 step sequence again before returning back another analysis for additional changes potentially needed.
    
          Keep repeating / iterating through this process with the four tools until our application is as optimized as possible for SEO, accessibility and performance.
    
    `,
          },
        ],
      })
    );
Behavior2/5

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 states the tool 'optimizes' the application, implying a mutation or action, but doesn't clarify what this entails—whether it makes changes, generates reports, requires specific permissions, has side effects, or produces output. 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, efficient sentence that directly states the tool's action and scope without unnecessary words. It is appropriately sized and front-loaded, with every part contributing essential information.

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 tool's complexity (implied by 'optimize' and multiple audit domains), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'optimize' means in practice, what the tool outputs, or how it differs from sibling tools, leaving the agent with insufficient context for effective use.

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 zero parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. A baseline of 4 is applied as per the rules for zero-parameter tools.

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 ('run') and target ('audit mode'), and specifies the optimization domains (SEO, accessibility, performance). However, it doesn't explicitly distinguish this from sibling audit tools like runAccessibilityAudit, runPerformanceAudit, and runSEOAudit, which appear to handle individual domains separately.

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. It doesn't mention when this comprehensive audit should be preferred over the individual domain-specific audit tools (e.g., runAccessibilityAudit), nor does it specify prerequisites, timing, or exclusions for its use.

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/oenius/browser-tools-mcp'

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