Skip to main content
Glama
Sign In
AgentSEO MCP Server

AgentSEO MCP Server

by AgentSEO-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

AgentSEO Page CRO QA

agentseo_page_cro_qa
Destructive

Audit SEO landing pages for value proposition clarity, CTA strength, trust proof, objection handling, and conversion friction to identify fixes that improve conversion readiness.

Instructions

Audit SEO landing pages for value proposition clarity, CTA strength, trust proof, objection handling, and conversion friction. Uses AgentSEO credits; repeating the call can create new charged work.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "agentseo_page_cro_qa"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoAbsolute web page URL to analyze; use an http:// or https:// URL. Type: String. Format: absolute URL. Optional; no client default.
htmlNoPage HTML supplied directly for analysis; provide this, markdown or a URL and avoid secrets in markup. Type: String. Minimum: 80 characters. Maximum: 250000 characters. Optional; no client default.
syncNoRequest a bounded wait for completion when true. The API can still return a pending job; retain its job ID and poll agentseo_job_status instead of repeating this charged call. False returns a queued job without waiting. Type: Boolean. Default: true.
targetNoYour target brand, domain or URL used to scope this workflow; supply the entity you want assessed. Type: String. Optional; no client default.
keywordNoSearch keyword or phrase to analyze for this workflow. Type: String. Optional; no client default.
audienceNoIntended reader or buyer group in plain language; do not include unnecessary personal data. Type: String. Maximum: 180 characters. Optional; no client default.
markdownNoPage Markdown supplied directly for analysis; provide this, html or a URL. Type: String. Minimum: 80 characters. Maximum: 50000 characters. Optional; no client default.
page_typeNoPage format or classification for this record; select one of the accepted values. Type: String. Accepted values: "auto", "homepage", "landing_page", "pricing", "feature", "blog_post", "product", "comparison_page", "docs". Default: "auto".auto
traffic_sourceNoAcquisition channel of the visitors this page is intended to convert. Type: String. Accepted values: "organic", "paid", "email", "social", "direct", "referral", "unknown". Default: "organic".organic
conversion_goalNoDesired visitor action used to evaluate conversion friction; no purchase or signup is performed. Type: String. Accepted values: "signup", "trial", "demo", "purchase", "contact_sales", "subscribe", "download", "learn_more". Default: "signup".signup

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.1.5
    • addedInput schema / properties / audience / description
      Added value: +"Intended reader or buyer group in plain language; do not include unnecessary personal data. Type: String. Maximum: 180 characters. Optional; no client default."
    • addedInput schema / properties / conversion_goal / description
      Added value: +"Desired visitor action used to evaluate conversion friction; no purchase or signup is performed. Type: String. Accepted values: \"signup\", \"trial\", \"demo\", \"purchase\", \"contact_sales\", \"subscribe\", \"download\", \"learn_more\". Default: \"signup\"."
    • addedInput schema / properties / html / description
      Added value: +"Page HTML supplied directly for analysis; provide this, markdown or a URL and avoid secrets in markup. Type: String. Minimum: 80 characters. Maximum: 250000 characters. Optional; no client default."
    • addedInput schema / properties / keyword / description
      Added value: +"Search keyword or phrase to analyze for this workflow. Type: String. Optional; no client default."
    • addedInput schema / properties / markdown / description
      Added value: +"Page Markdown supplied directly for analysis; provide this, html or a URL. Type: String. Minimum: 80 characters. Maximum: 50000 characters. Optional; no client default."
    • addedInput schema / properties / page_type / description
      Added value: +"Page format or classification for this record; select one of the accepted values. Type: String. Accepted values: \"auto\", \"homepage\", \"landing_page\", \"pricing\", \"feature\", \"blog_post\", \"product\", \"comparison_page\", \"docs\". Default: \"auto\"."
    • addedInput schema / properties / sync / description
      Added value: +"Request a bounded wait for completion when true. The API can still return a pending job; retain its job ID and poll agentseo_job_status instead of repeating this charged call. False returns a queued job without waiting. Type: Boolean. Default: true."
    • addedInput schema / properties / target / description
      Added value: +"Your target brand, domain or URL used to scope this workflow; supply the entity you want assessed. Type: String. Optional; no client default."
    • addedInput schema / properties / traffic_source / description
      Added value: +"Acquisition channel of the visitors this page is intended to convert. Type: String. Accepted values: \"organic\", \"paid\", \"email\", \"social\", \"direct\", \"referral\", \"unknown\". Default: \"organic\"."
    • addedInput schema / properties / url / description
      Added value: +"Absolute web page URL to analyze; use an http:// or https:// URL. Type: String. Format: absolute URL. Optional; no client default."
  2. First observedv0.1.4

TDQS

A3.7/5.0
Behavior4/5

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

The cost and repeat-charge warning adds concrete behavior beyond annotations, and it corroborates the non-idempotent, open-world profile. It does not address what the destructiveHint=true annotation implies for an audit operation, nor does it describe rate limits or what a returned audit contains.

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?

Two sentences, purpose front-loaded before the cost caveat, with no filler. Every clause carries information an agent needs before calling.

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?

With 10 optional parameters, an async/charged workflow, and no output schema, the description covers the intent and the billing risk but says nothing about what the audit returns (scores, findings, recommendations) or how multiple input sources are prioritized. Adequate but with a clear gap for a tool this flexible.

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% and the schema already documents the url/html/markdown trade-off and the sync polling behavior, so the description adds essentially no parameter meaning. Baseline 3 applies; nothing in the prose explains how target, keyword, audience, or page_type interact.

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 gives a specific verb ('Audit') and resource ('SEO landing pages') and enumerates the exact review dimensions — value proposition clarity, CTA strength, trust proof, objection handling, conversion friction. That makes it clearly distinguishable from nearby QA siblings like agentseo_content_draft_qa or agentseo_content_technical_qa, though it never names them.

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?

It notes the credit cost and that repeating the call creates new charged work, which is real usage guidance, and the schema's sync description routes agents to agentseo_job_status for pending jobs. However, there is no explicit when-to-use/when-not-to-use statement versus the other QA tools (draft QA, technical QA), so selection still relies on inference.

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

Deploy Server

Other Tools