Skip to main content
Glama

Update draft

update_draft
DestructiveIdempotent

Saves edits to the article of a content calendar topic (its newest draft), the same as saving it in Content Studio. Send only the fields to change: title, slug, seoTitle, seoDescription, contentMarkdown or structuredDataEdit; the others keep their values. contentMarkdown replaces the whole text: read the article with get_draft just before you send it, because the last save wins, and a save made in Content Studio between the two calls is lost. When the text starts with a # heading, that heading is the title: the first heading follows the title on each save (the new title, else the current one), and text without a leading heading stays as it is. Keep each [[youtube:ID]] token and each image URL that stays in the article; an image whose URL is no longer in the text is removed from the article. A slug that another article of the site uses is refused (article_slug_taken). The summary and the hero image cannot be edited here. A text edit of a published article does not change the live page: it keeps the old text until the article is published again. structuredDataEdit replaces the owner’s whole Structured Data Edit, the changes to Keytomic’s structured data (JSON-LD); read it with get_draft just before you send it, because the last save wins. When get_draft gives liveUpdate on_save for the destination, the save also sends the structured data alone to the live WordPress post: the text, the URL and the dates of the post do not change. That send needs the content:publish scope and the user’s publish permission; without them the edit saves, and structuredDataSave.liveError says why the live post did not change. Name destinationId as in get_draft. Returns the updated article, the same as get_draft, and structuredDataSave (liveUpdate, sent, liveError) when the call saved structured data. Spends no credits.

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": {
      "projectId": "<projectId>",
      "topicId": "<topicId>"
    },
    "name": "update_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoURL slug of the article, such as how-to-bake-sourdough. A slug that another article of the site uses is refused.
titleNoThe article title.
topicIdYesTopic whose article to edit, from list_calendar_topics.
seoTitleNoTitle for search results. null clears it.
projectIdYesSite to act on, from list_sites.
destinationIdNoPublishing destination whose live post a structured data save can update, from the destinations section of get_project. Leave it out to use the site’s only active destination.
seoDescriptionNoDescription for search results. null clears it.
contentMarkdownNoThe full article text as Markdown. It replaces the whole text. When the text starts with a `# ` heading, the first heading follows the title; keep each `[[youtube:ID]]` token and each image URL that stays in the article.
structuredDataEditNoThe owner’s whole Structured Data Edit. It replaces the saved edit: nodes holds the JSON-LD nodes that replace or add to Keytomic’s, at most one for each schema type, and removedTypes holds the schema types to remove from Keytomic’s. Send { "nodes": [], "removedTypes": [] } to clear the edit.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

The annotations already mark this as a destructive, idempotent, open-world mutation, and the description adds substantial behavior beyond them: overwrite semantics, lost-update races with Content Studio, image removal when URLs disappear, slug refusal, live WordPress structured-data sending, required scopes/permissions, and the structuredDataSave.liveError fallback. It even states that the call spends no credits.

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 purpose and partial-update rule are front-loaded, and most sentences carry useful behavioral detail. It is dense and presented as one long paragraph, with some repetition of the read-before-send and last-save-wins rules for two parameters, so it could be structured more cleanly.

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 9-parameter destructive tool with a nested structuredDataEdit object and no output schema, the description covers the return value, live-update side effects, permission requirements, error field, slug conflict, image handling, and publish-state caveats. Nothing essential for correct invocation appears to be missing.

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, but the description adds important partial-update semantics: only changed fields need to be sent and the others keep their values. It also reinforces the replacement behavior of contentMarkdown and structuredDataEdit and the read-before-send requirement, though some details duplicate the schema descriptions.

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 states a specific verb and resource: it saves edits to the article of a content calendar topic, specifically its newest draft. It also anchors the operation to Content Studio and distinguishes it from reading with get_draft and republishing, so an agent can identify it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to send only the fields to change and to read the article with get_draft just before sending because the last save wins. It also gives concrete exclusions and conditions: summary and hero image cannot be edited here, published text stays unchanged until republished, and destinationId should come from get_draft.

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