suede-skills-mcp

Suede Live Page Audit

suede_live_page_audit

Read-onlyIdempotent

Audit a public URL for crawler and AI answer-engine visibility, with A-F grades, checks for status, HTTPS, noindex, robots.txt, metadata, structured data, and top fixes.

Instructions

Fetch a public URL and grade what crawlers and answer engines actually receive: status, HTTPS, noindex, robots.txt for Google and AI answer bots (ChatGPT, Perplexity, Claude), canonical, title, description, H1, readable text, JSON-LD, FAQ, llms.txt, sitemap, calls to action and share previews. Returns an A-F grade per lane, every check, and the top fixes.

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": "suede_live_page_audit"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Public http(s) URL to audit. A bare domain is treated as https.
`primaryAction`	No	Optional main action the page should drive, checked against its links and buttons.

Output Schema

Name	Required	Description	Default
`ok`	Yes
`page`	No
`error`	No
`lanes`	No
`checks`	No
`robots`	No
`status`	No
`fetchMs`	No
`overall`	No
`finalUrl`	No
`topFixes`	No
`fetchedAt`	No
`htmlBytes`	No
`notChecked`	No
`requestedUrl`	No
`htmlTruncated`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds real value beyond that by spelling out what is inspected (status, HTTPS, noindex, robots.txt for named AI bots, canonical, JSON-LD, llms.txt, sitemap, share previews) and what comes back (A-F grade per lane, every check, top fixes). It does not note rate limits, latency, or what happens on blocked/unreachable pages, which keeps it below a 5.

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 action verb and scope are front-loaded, and the check list plus return summary are packed into two efficient sentences with no filler. The middle sentence is a long enumeration, but every listed item is concrete and earns its place by defining audit coverage.

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

Completeness4/5

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

With a full input schema, an output schema, and annotations covering safety and open-world behavior, the description supplies the remaining needed context: the breadth of checks and the shape of the result. Only the sibling differentiation and edge-case behavior (unreachable pages, bot-blocked fetches) are missing, which are minor for a read-only audit tool.

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 both parameters are documented in the schema, including the bare-domain-as-https behavior, so the baseline is 3. The description adds no parameter-level meaning and never mentions the optional primaryAction, so it does not exceed the baseline.

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 opens with a specific verb and resource ('Fetch a public URL and grade what crawlers and answer engines receive') and enumerates the exact checks performed. It stops short of differentiating the tool from close siblings such as suede_visibility_grade or suede_copy_seo_audit, so an agent cannot fully disambiguate from the name and description alone.

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 by the scope ('a public URL' and what 'crawlers and answer engines actually receive'), which tells the agent this is a live-page crawlability/SEO audit. However, there is no explicit when-to-use, when-not-to-use, or comparison against the clearly overlapping siblings like suede_visibility_grade, leaving the routing decision to inference.

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

Deploy Server