Skip to main content
Glama

SEO audit results

recipe__seo_audit
Read-onlyIdempotent

Daily SEO audit for every connected site with an active Royal MCP Pro license, using the plugin's own checks on published pages and posts: the SEO plugin in use, per post type how many items were audited and how many have issues, counts by issue type (title_* and description_* length or missing problems, noindex_true, h1_missing, h1_multiple, h1_unverifiable_theme_title, no_featured_image, images_missing_alt, images_unverifiable_shortcode), the worst pages with their issues, the site's bands on the Royal SEO Standard (indexability, on-page, content, technical and ai_eligibility, each healthy, needs_attention, at_risk or not_enough_data, with a score rounded to 5 and its failing checks, plus which AI training crawlers robots.txt allows), Google Search Console results for the last 28 days against the period before (clicks, impressions, CTR, average position, top pages and the pages moving most; reported, never scored; read through the agency's Google or SEObolt connection on the Integrations page, or else through SEObolt Pro on the site), each site's three most important fixes with who makes them and its count of open findings (recipe__seo_findings lists every fix and page for one site), page_checks (the site's own checks of its five most important pages, three on Rank Math sites, with Royal MCP Pro 1.0.14, and checked_at for when they last ran: schema for structured data and rendered for duplicate main headings, tables of contents, a repeated excerpt and leftover shortcodes, each checked, not_available (reason needs_update when the site's Royal MCP Pro is older than 1.0.14, otherwise unavailable) or failed; a check that could not run is never a pass; on Rank Math sites rank_math lists each page's saved Rank Math score, where a null score means not analysed yet, never zero; on SEObolt Pro sites seobolt_geo lists each page's AI search visibility score out of 100 with its weakest factors and the average, where a null score means the read failed), and open SEO alerts (search engines discouraged, a noindexed home page, robots.txt or a noindex header blocking important pages, a broken SSL certificate, AI search crawlers blocked). A site where Royal MCP Pro's license has lapsed is listed with status unlicensed and no findings, because Royally cannot audit it; sites the audit does not cover are listed under not_monitored with the reason. Use this to plan SEO work; write changes with the site's own *_bulk_update_meta tool, which previews before it commits.

Input Schema

NameRequiredDescriptionDefault
site_idsNoOnly these sites. Omit for every monitored site.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Far beyond what readOnlyHint/idempotentHint provide: it discloses license gating (lapsed sites appear as status unlicensed with no findings), the not_monitored bucket and its reason, that GSC numbers are 'reported, never scored', that a check which could not run is 'never a pass', and null-score semantics for Rank Math vs SEObolt.

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

Conciseness2/5

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

A single run-on sentence with several levels of nested parentheses enumerating dozens of issue-type tokens and per-page check names. Information is front-loaded but effectively unscannable; the taxonomy dump crowds out the decisions an agent actually needs.

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?

No output schema exists, and the description carries the full return-shape burden: per-post-type audit counts, issue counts, worst pages, Royal SEO Standard bands, GSC comparison, page_checks with per-check statuses. Nothing needed to interpret the response is missing.

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?

One optional site_ids parameter with 100% schema coverage that already states 'Omit for every monitored site.' The description reinforces what 'monitored' means via the not_monitored/unlicensed rules but adds no syntax or format guidance beyond the schema.

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?

Opening clause names the verb, resource and scope: a daily SEO audit of every connected site with an active Royal MCP Pro license, run with the plugin's own checks. It also distinguishes itself from the sibling recipe__seo_findings, which is explicitly described as the per-site detail tool.

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?

Closes with explicit routing: 'Use this to plan SEO work; write changes with the site's own *_bulk_update_meta tool, which previews before it commits,' and points to recipe__seo_findings for per-fix, per-page detail. Missing a crisp statement of what it is NOT for (e.g. when a per-site or single-check tool is preferable).

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