Skip to main content
Glama

royal-mcp__seo_optimize_for_launch

Destructive

[Royal MCP Pro] Transactional launch composer for a single post: SiteVault pre-snapshot → audit stored SEO title/description → auto-fix meta (opt-in) → verify JSON-LD schema present on rendered post → create 301 redirects from old slugs → push URL to IndexNow (Bing / Yandex, opt-in) → push URL to Google Search Console via Site Kit (opt-in) → purge the post URL in every active cache layer (ForgeCache, LiteSpeed Cache, W3 Total Cache, WP Rocket, WP Super Cache, Cloudflare; published posts only). Refuses code snippets, revisions, attachments, menu items and trashed / auto-draft posts. Default compose_mode=strict — a failing write sub-op (meta fix, redirects) aborts + reverses reversible sub-ops; failures to reverse are listed in rollback_failures. Schema verify, IndexNow, Search Console and cache purge never abort or roll back: a failure is reported as skipped ("not sent: ..." / "not purged: ...") and listed in warnings. Auto-fixed descriptions never use the body of a password-protected or private post. Use com… Through Royally: waits for a person to approve it in Royally; nothing on the site changes until then.

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": {
      "post_id": "<post_id>"
    },
    "name": "royal-mcp__seo_optimize_for_launch"
  }
}

Input Schema

NameRequiredDescriptionDefault
fixesNoPer-sub-op toggles. Meta-write flags default false (opt-in, mutate live user-facing content). Additive/idempotent sub-ops (schema verify, cache purge) default true. External-service pushes (IndexNow, GSC) default false (opt-in — hit third-party endpoints).
post_idYesPost ID to optimize. Caller must have edit_post capability on the target post.
site_idNoSite to run this tool on: 8ef2e52b-bd07-4671-a363-ebe8b480b65c (https://demo.royalplugins.com)
snapshotNoIf true (default), trigger a SiteVault snapshot before any writes. Skipped-with-note when SiteVault is not installed. Undo does NOT restore from snapshot — invoke SiteVault directly for full-site restore.
compose_modeNostrict aborts + rolls back on first error; best_effort continues past failures; report_only returns the plan for write sub-ops AND executes read-only sub-ops (audit / schema-verify) so callers get real findings from a dry-run. Write sub-ops never mutate in report_only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / fixes / properties / purge_cache / description
      Previous value: -"If true (default), purge cache on the post URL. Auto-detects ForgeCache / WP Rocket / W3TC / WP Super Cache. Skip-with-note when no cache plugin detected."New value: +"If true (default), purge the post URL in every active cache layer (ForgeCache, LiteSpeed Cache, W3 Total Cache, WP Rocket, WP Super Cache, Cloudflare). Skip-with-note when no cache layer is active or the post is not published."
  2. Added
  3. Removed
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (destructive, openWorld, non-idempotent), the description discloses rollback semantics (strict aborts and reverses reversible sub-ops, with rollback_failures listed), which sub-ops never abort (schema verify, IndexNow, GSC, cache purge report as skipped with warnings), and the Royally human-approval gate. It also notes auto-fix never uses body text of password-protected/private posts — rich, non-obvious behavioral context.

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 pipeline is front-loaded as an arrow chain, which is efficient for a multi-step tool, and the failure-policy paragraph is well organized. It is long and repeats some opt-in/default information that the schema already states, costing a point.

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 complex, destructive, multi-sub-op tool with no output schema, the description covers failure modes, rollback, skipped-step reporting, refusal conditions, and the approval gate — everything an agent needs to call it safely. Return-value details are partially covered via named fields (rollback_failures, warnings, data.self_redirect_skipped).

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%, so the baseline is 3; the description adds meaning on top by explaining compose_mode's default and abort/rollback consequences and the opt-in rationale for meta-write and external-push flags. It stops short of detailing every nested toggle, which the schema already covers well.

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?

The description opens with a specific verb+resource ('Transactional launch composer for a single post') and then enumerates the exact pipeline steps (snapshot, meta audit/fix, schema verify, 301s, IndexNow, GSC, cache purge). This makes it clearly distinguishable from read-only siblings like seo_audit_meta_tags or wp_get_seo_meta, which only inspect metadata.

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?

It states explicit exclusions ('Refuses code snippets, revisions, attachments, menu items and trashed / auto-draft posts') and explains the three compose_mode behaviors, including that report_only executes read-only sub-ops for a real dry-run. It does not explicitly name a sibling to use instead for pure auditing, so it falls short of a 5.

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