Skip to main content
Glama

Update post

update_post
Destructive

Edit an existing draft/scheduled post without deleting it. You may change its base content, target platforms, status, scheduled time, per-platform settings, and/or APPEND media from public https URLs via mediaUrls. Set publishNow=true to publish using server time; it consumes monthly quota but no deferred queue slot, even when that queue is full. It re-validates the complete final content/media/platform state. Appending does not replace unfinished upload slots: inspect get_post and use delete_media for that specific reservation first only when the user's task authorizes abandoning it. Before changing platforms, call list_connections and copy each target's platformId verbatim. Published/failed posts and posts already being published are not editable. Scheduling re-validates the complete final content/media/platform state; omitting a field keeps its current value.

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": {
      "postGroupId": "<postGroupId>"
    },
    "name": "update_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
statusNoNew status: 'draft' or 'scheduled'. publishNow=true schedules immediate publication; omit status or use 'scheduled'. Combining it with 'draft' is rejected.
contentNoOptional replacement base post text. On X and Threads, long content auto-splits into a chain; a standalone --- line between paragraphs sets a break, and media attach only to the first part. Threads parts are limited to 500 characters; the connection needs threads_manage_replies, and THREADS_PERMISSION_REQUIRED means reconnect in Publora Channels. Thread part and numbering settings are not API/MCP inputs. After partial publication, inspect get_post and never recreate or resubmit the whole chain. For an unknown outcome, check the live account before further action. Updates every target without an explicit platform-specific override. An empty string is allowed for a draft; scheduling still enforces each platform's content/media rules.
mediaUrlsNoOptional array (max 10) of public https URLs of images/videos to APPEND to this post. Same rules as create_post: direct file URLs only; jpeg, png, gif, webp, tiff, avif, mp4, mov, webm; images ≤25MB, videos ≤150MB.
platformsNoOptional replacement target platform array. Call list_connections first and copy its platformId values verbatim. This replaces the whole set; [] is allowed only while the post remains a draft.
publishNowNoSet true to publish this draft or scheduled post immediately using server time and trigger publication processing. Reserves monthly publication quota but no deferred queue slot. Omit scheduledTime and status; a future time or status 'draft' is rejected. False or omitted retains existing editing/scheduling behavior. Inspect get_post for asynchronous publication progress.
postGroupIdYesPost group ID
firstCommentNoReplace the first comment (object) or clear it (null). Legacy single first comment under your own post. Supported: linkedin (profiles and Pages), twitter, threads, bluesky, mastodon; other targets are skipped. Best effort: read firstCommentResult via get_post. Cannot be combined with firstComments or added after publishing.
firstCommentsNoReplace all first comments (array of up to 3), or clear with null or []. Up to 3 ordered first comments under your own post, each { text, platforms?, delaySeconds? }. delaySeconds is an integer 0–86400; omitted means 0. The next comment runs only after the previous one posts, on a scheduler tick; a failed comment stops later ones. Platform types (not connection keys) and text limits follow firstComment. Best effort, no blind retries. Read per-target firstCommentResults via get_post. Cannot be combined with firstComment or added after publishing.
scheduledTimeNoNew ISO 8601 date-time with UTC Z or offset. Choose a future time within the schedule horizon returned by account_context. With publishNow=true, omit this field; a future scheduledTime is rejected. Inspect returned warnings and effective scheduledTime; a quota error requires changing the request or queue state before retrying.
idempotencyKeyNoOptional retry key. Reusing it with the identical request prevents repeated media appends and replays the original response.
platformSettingsNoMerge per-platform options (same shape as create_post). Per-platform options keyed by platform. Example: { instagram: { coverUrl: 'https://.../cover.jpg' }, youtube: { title: 'My video', tags: ['topic'] }, tiktok: { viewerSetting: 'SELF_ONLY' }, twitter: { replyTo: 'https://x.com/user/status/123' } }. Also supports telegram.disableNotification/disableWebPagePreview/protectContent, threads.replyControl, linkedin.repostParentUrn/repostVisibility. For TikTok photos, tiktok.autoAddMusic lets TikTok choose music; no track selection or preview. Unknown platforms or fields are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / platformSettings / properties / tiktok / properties / allowComments / description
      Added value: +"Default false for new posts. Enable comments only after the creator explicitly opts in; omission on update preserves the saved choice."
    • addedInput schema / properties / platformSettings / properties / tiktok / properties / allowDuet / description
      Added value: +"Default false for new posts. Enable Duet only after the creator explicitly opts in; omission on update preserves the saved choice."
    • addedInput schema / properties / platformSettings / properties / tiktok / properties / allowStitch / description
      Added value: +"Default false for new posts. Enable Stitch only after the creator explicitly opts in; omission on update preserves the saved choice."
  2. Changed4 schema fields changed
    • addedInput schema / properties / platformSettings / properties / instagram / properties / aiGenerated
      Added value: +{
      +  "description": "Self-disclose AI-generated content: adds Instagram's \"AI info\" label (is_ai_generated). Required by Meta for realistic AI-generated or AI-altered video, audio or images. Cannot be added or removed after publishing. Default false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / platformSettings / properties / tiktok / properties / aiGenerated
      Added value: +{
      +  "description": "Self-disclose AI-generated content: adds TikTok's \"Creator labeled as AI-generated\" label (is_aigc). Required for realistic AI-generated video or images; missing disclosure risks removal or loss of For You eligibility. Default false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / platformSettings / properties / twitter / properties / aiGenerated
      Added value: +{
      +  "description": "Self-disclose that the post contains AI-generated media (X made_with_ai, shown as \"Made with AI\"). Sent only when the post attaches media; a text-only post is published without it. Voluntary on X in general; mandatory for AI videos of armed conflicts by creators in revenue sharing. Default false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / platformSettings / properties / youtube / properties / aiGenerated
      Added value: +{
      +  "description": "Self-disclose altered or synthetic content (status.containsSyntheticMedia). Required for realistic AI-generated or AI-altered video or audio; not needed for scripts, titles, thumbnails, beauty filters or clearly unrealistic content. Default false.",
      +  "type": "boolean"
      +}
  3. Changed2 schema fields changed
    • changedInput schema / properties / platformSettings / description
      Previous value: -"Merge per-platform options (same shape as create_post). Per-platform options keyed by platform. Example: { instagram: { coverUrl: 'https://.../cover.jpg' }, youtube: { title: 'My video', tags: ['topic'] }, tiktok: { viewerSetting: 'SELF_ONLY' }, twitter: { replyTo: 'https://x.com/user/status/123' } }. Also supports telegram.disableNotification/disableWebPagePreview/protectContent, threads.replyControl, linkedin.repostParentUrn/repostVisibility. Unknown platforms or fields are rejected."New value: +"Merge per-platform options (same shape as create_post). Per-platform options keyed by platform. Example: { instagram: { coverUrl: 'https://.../cover.jpg' }, youtube: { title: 'My video', tags: ['topic'] }, tiktok: { viewerSetting: 'SELF_ONLY' }, twitter: { replyTo: 'https://x.com/user/status/123' } }. Also supports telegram.disableNotification/disableWebPagePreview/protectContent, threads.replyControl, linkedin.repostParentUrn/repostVisibility. For TikTok photos, tiktok.autoAddMusic lets TikTok choose music; no track selection or preview. Unknown platforms or fields are rejected."
    • addedInput schema / properties / platformSettings / properties / tiktok / properties / autoAddMusic
      Added value: +{
      +  "description": "Photo Direct Post only. Opt in with true to let TikTok automatically choose music; Publora cannot select or preview a specific track. False disables music and is allowed when switching to video. Omission preserves existing behavior. Videos never send this parameter.",
      +  "type": "boolean"
      +}
  4. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Well beyond the annotations: it discloses quota vs deferred-queue-slot effects of publishNow, that the complete final content/media/platform state is re-validated, that appending does not replace unfinished upload slots, that omission preserves current values, and that idempotencyKey replays the original response. The async-publication behavior is only pointed at via get_post rather than described, which keeps this below a 5. Nothing contradicts destructiveHint=true or idempotentHint=false.

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?

Purpose and scope are front-loaded, and nearly every clause carries operational weight (quota, validation, media-slot caveat, platformId verbatim). It is dense and run-on in places — the media-slot and re-validation points are repeated — but there is little outright filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter mutating tool with nested platformSettings and no output schema, the description covers safety, validation, quota, retry, and result-discovery paths. The main gap is that the immediate update response is only implied ("inspect returned warnings and effective scheduledTime") rather than stated, leaving some inference about what a successful call returns.

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 earns above that by clarifying the highest-risk semantics: mediaUrls APPENDS rather than replaces, publishNow consumes quota but no queue slot, platform IDs must be copied verbatim from list_connections, and omitted fields retain current values. It does not restate limits already in the schema, which is appropriate.

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 and resource ("Edit an existing draft/scheduled post without deleting it") and immediately bounds which posts qualify. The edit-vs-delete framing separates it from delete_post, and the field list (content, platforms, status, scheduledTime, settings, mediaUrls) tells an agent exactly what surface it covers.

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?

Gives explicit exclusions ("Published/failed posts and posts already being published are not editable") and routes to named siblings: get_post for inspection, delete_media for abandoning a specific reservation, list_connections before changing platforms, account_context for the schedule horizon. It also sets a prerequisite (authorization) before destructive side-stepping.

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.