Skip to main content
Glama

SEO Rank Fixer

Scan a page

scan_page
Read-onlyIdempotent

Checks any public web page, plus up to 4 more pages of the same site (from its sitemap or links), for SEO, answer-engine and AI-crawler problems (indexing, robots.txt and AI bot access, title, description, headings, canonical, redirects, sitemap, llms.txt, structured data and Organization markup, images, link text, page weight and scripts, mixed content, question-and-answer content, authors and dates, broken internal links, duplicate titles, Core Web Vitals from Google) and scores it out of 100 overall and per channel (SEO, AEO, GEO). Each finding includes the evidence read from the site and a link to the guidance; a finding seen on several pages says which ("3 of 5 pages ..."). Passed checks and the pages read are listed too. It answers within a few seconds: checks the site (or Google's speed test) did not answer in time are named in notes and the reply is marked partial. A recent scan of the same page is reused for 10 minutes. When the page cannot be read (site down, blocking bots, not a web page), the reply says why.

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": {
      "url": "<url>"
    },
    "name": "scan_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe page, e.g. https://example.com/pricing

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive/open-world, yet the description adds substantial behavior: a few-second time budget, partial-result flagging with named timeouts, a 10-minute reuse window for recent scans, and explicit failure reporting rather than silent errors. It also discloses the shape of the response (findings with evidence plus guidance link, cross-page counts like '3 of 5 pages', passed checks, pages read).

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

Conciseness3/5

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

Purpose and scope are front-loaded, but the check enumeration in parentheses runs roughly twenty items and turns the definition into one very long sentence. The time-budget, caching, and failure details are valuable; the exhaustive taxonomy of checks is lower-value bulk.

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?

There is no output schema, so the description must explain returns, and it does: scoring out of 100 overall and per channel, findings with evidence and guidance links, passed checks, pages read, and partial-result notes. Caching and error behavior round out what an agent needs to call it and interpret the reply.

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 coverage is 100% and the single url parameter already has an example, so the schema carries most of the load. The description still adds meaning: the URL must be a public web page, and that one URL expands into up to four additional pages of the same site, which is non-obvious from a single string parameter.

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?

States a specific verb and resource ('Checks any public web page') and bounds scope precisely ('plus up to 4 more pages of the same site (from its sitemap or links)'), which implicitly separates it from site-wide siblings like site_audit. It stops short of naming a sibling alternative explicitly, so it is clear but not fully differentiated.

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

Usage Guidelines3/5

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

Usage is implied: it is for single-page checks with a small crawl up to 5 pages, and it documents the failure contexts ('site down, blocking bots, not a web page'). There is no explicit statement of when to prefer this over site_audit, site_performance, or index_status, so the agent must infer the boundary.

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.