page

Call page.write_article

Put a finished article on a site's blog — 'add this post to the blog', 'put this write-up on my site', 'I want this article on the site'. Write a finished article into a site's blog. YOU write the article — pass the headline, a one-sentence summary and the body as subheadings with their paragraphs; nothing here generates copy for you. It does NOT publish: the post is stored and the site is rebuilt, and page.publish_article is what puts it in front of readers. If build_run_id is missing, say the rebuild has not started. Not for putting the article in front of readers — that is page.publish_article.

Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.

post/api/v1/tools/page.write_article

Request

  • Base URL: https://app.goosybear.ai
  • URL: https://app.goosybear.ai/api/v1/tools/page.write_article
  • Auth: HTTP bearer

Headers

x-request-idstring

Your own id for this request, echoed back and recorded on the audit trail. 1–128 characters from A–Z a–z 0–9 . _ : -, starting with a letter or digit; anything else is replaced by a generated id.

Request body

site_idstring uuid

The SITE the member means, as a site UUID. You are NOT shown the id of the site open on screen — it never appears in your context, so there is nothing to copy. When they say 'this site', 'the site I'm looking at', or name no site at all, they mean that on-screen site, and the way to reach it is: where this schema leaves site_id OPTIONAL, OMIT IT ENTIRELY — that is the primary path, not a fallback, and the turn's own surface resolves it server-side. Where the schema REQUIRES it, call page.list with name set to the site they named — it returns that one site's id, or the candidates to ask them about. Never pass a board, board-item, thread or any other id that merely happens to be nearby in the conversation — those name different objects and will be refused — and never one you composed.

titlestring required

The article headline, as it should appear. Write it — do not ask the tool to invent one.

summarystring required

One sentence. It becomes the page's meta description and the archive card's summary, so make it describe the article rather than tease it.

slugstring

Optional URL slug. Leave it out to derive one from the title. A slug that already exists on this site is refused rather than suffixed — a second permanent URL is not what the operator asked for.

author_namestring

Optional byline. Leave it out unless the operator named an author — an invented author is a claim on their site.

image_urlstring

Optional absolute https URL of the lead image. Leave it out unless the operator supplied one.

workspacestring

Which workspace to run in — its slug. Omit to use your default. With more than one reachable workspace and no default, the call is refused and the choices are listed.

Response

The call was admitted and dispatched. ok says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.

OR

Changes

No recorded changes to this operation across all 5 revisions of this API.