Skip to main content
Glama
Hermoso

Hermoso

Official

Publish a WordPress blog post

post_to_wordpress
Destructive

Publish, draft, or schedule a WordPress blog post from a title and body, including featured or inline images, video, categories, and tags.

Instructions

Use this when the user wants to publish, draft or schedule a BLOG POST on their WordPress site. Publishing costs no credits. A title is REQUIRED and the text becomes the body: plain text or light markdown (## headings, - lists, bold, links) is turned into WordPress blocks, and HTML is sent as written. status: publish (default), draft, pending (submit for review), private (logged-in editors only) or future with a date — a future date makes WordPress schedule it natively. The FIRST image becomes the FEATURED image, every other image is uploaded and placed inline, and a video is uploaded and embedded (if the site's host refuses the file as too large, the post plays it from its own link and the reply says so). categories and tags take names or ids; a name the site lacks is CREATED and the reply says which. An over-long title is refused, never cut. WordPress has NO per-post views in its API: never quote a view count for a WordPress post. Works on a self-hosted site and on a site hosted on WordPress.com, whichever the brand connected. Not connected: the user connects it under Connectors > WordPress, or you call connect_connector with provider wordpress (siteUrl, username, appPassword).

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": {
      "title": "<title>"
    },
    "name": "post_to_wordpress"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoISO time to publish at; a future date schedules it on WordPress itself
hookNothe post's angle — a list_hooks id or your own wording, reused exactly
slugNothe end of the post URL
tagsNotag names or ids (a missing name is created)
textNothe body: plain text, light markdown or HTML
brandNoWHICH PROFILE this post belongs to — id or exact name from list_brands (a shared workspace: its profile id). Beats the connection's pin for THIS CALL ONLY; a name that matches no profile, or two, is REFUSED and nothing is posted.
titleYesREQUIRED — the post title
ideaIdNoshort id of the content-plan idea this post came from
recipeNothe post's FORMAT id, e.g. "slideshow" or "imessage_chat" — post_performance groups by it, so reuse one id per format
statusNodefault publish
altTextNoalt text for the images
excerptNothe summary under the title in lists and search
subjectNowhat the post is about
imageUrlNoone image — becomes the featured image
videoUrlNoone video, embedded in the post
imageUrlsNoseveral images: the first is featured, the rest go inline
categoriesNocategory names or ids (a missing name is created)
allowDuplicateNopost it even though an identical post was just made
idempotencyKeyNoany stable string: a repeat within 24h returns the original post instead of posting again

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.571

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description goes well beyond them: cost (no credits), the markdown-to-blocks and HTML pass-through conversion, featured-vs-inline image ordering, video upload with a link fallback when the host rejects file size, category/tag auto-creation with a reply notice, refusal rather than truncation of over-long titles, and the explicit warning that WordPress exposes no per-post view counts. It also notes idempotency via the 24h key. No statement conflicts with the annotations.

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?

Front-loaded with the when-to-use trigger, then packed with operational facts in a single dense paragraph; almost every sentence carries non-obvious information (conversion rules, image ordering, name creation, view-count caveat). It is on the long side and could be split into short bullets, but there is little pure filler.

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 19-parameter, mutation-heavy, open-world tool with no output schema, the description supplies the missing behavioral contract: scheduling semantics, media handling, auto-creation side effects, refusal behavior, cross-environment (self-hosted vs WordPress.com) support, and the setup path when unconnected. An agent has enough to call it correctly without guessing.

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 baseline is 3, but the description adds real meaning on top: it explains what status values mean (pending = submit for review, private = logged-in editors only, future + date = native WordPress scheduling), how categories/tags resolve names to ids and create missing names, and how imageUrl/imageUrls interact with the featured image. It leaves some 19-param surface (hook, recipe, ideaId, altText, subject) entirely to 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?

States a specific verb set (publish, draft, schedule) with a specific resource (BLOG POST) on a named platform (WordPress site), and additionally pins the target as self-hosted or WordPress.com. An agent can distinguish it from post_to_webflow, post_to_wix or post_to_shopify_blog purely from this sentence.

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?

Opens with an explicit when-to-use trigger ('when the user wants to publish, draft or schedule a BLOG POST') and names the fallback path when no connection exists (connect_connector with provider wordpress, siteUrl, username, appPassword). It does not state explicit exclusions versus other blogging siblings, but the platform naming effectively routes the agent, so this is clear context without formal when-not rules.

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