Skip to main content
Glama

Visibility Genies

Read audit pages

get_audit_pages
Read-only

Lists the pages a site audit crawled with status, fetch result (with the reason in failText when a page could not be loaded), title, size and link counts, plus Lighthouse scores for the pages it tested. Free: reads saved audit data. Lighthouse scores come from one lab test per device, not from real visitors, and INP is not measured, so Total Blocking Time stands in for it. Omit auditId for the audit Site Audit shows.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>"
    },
    "name": "get_audit_pages"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost pages to return (default 100).
auditIdNoAudit ID. Leave it out to use the audit Site Audit opens: the newest completed audit of the project's own site that read at least one page (until one exists, the latest audit of any kind).
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
fetchClassNoHow the page read ended. "blocked" means bot protection challenged the crawler; "rate_limited" means a 429 stopped the read; "error" means the page could not be loaded, and failText says why.
statusCodeNoOnly pages with exactly this HTTP status.
urlContainsNoOnly pages whose URL contains this text.
withLighthouseNoOnly pages that Lighthouse tested.

Output Schema

NameRequiredDescriptionDefault
metaNo
pagesYes
totalYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare this a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds substantial information beyond them: the call is free, failText carries the load-failure reason, and the Lighthouse numbers are lab data per device rather than field data, with INP unmeasured and Total Blocking Time substituted. That last caveat prevents a serious misreading of returned metrics.

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

Conciseness4/5

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

The main behavior is front-loaded in the first sentence, and the metric caveats and default-audit rule follow in a logical order. It is dense but not padded; the Lighthouse clarification is longer than strictly necessary, though it earns its place given how easily the scores would be misread.

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

Completeness5/5

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

For a read-only, seven-parameter tool with a full output schema and complete schema coverage, the description supplies everything the structured fields cannot: billing status, default-audit resolution, failure semantics, and the lab-vs-field caveat on Lighthouse data. Nothing an agent needs in order to call it or interpret it correctly is missing.

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?

Schema description coverage is 100%, so the parameters are already documented and a baseline of 3 applies. The description still adds value by reinforcing the auditId omission rule and by tying the fetchClass 'error' case to the failText field, explaining how two returned values relate rather than just what to pass.

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?

Names a specific verb and resource (lists crawled pages of a site audit) and enumerates the returned fields: status, fetch result, title, size, link counts, Lighthouse scores. That makes it clearly distinct from get_audit_issues (problems) and get_audit_status (run state) among its siblings.

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

Usage Guidelines4/5

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

Gives real operational guidance: 'Free: reads saved audit data', and 'Omit auditId for the audit Site Audit shows', which tells the agent how to invoke it without any prior lookup. It stops short of explicitly naming an alternative tool or stating when it should be avoided (e.g. versus get_audit_issues), so it is not a full when/when-not pair.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources