Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

posts_publish

Destructive

Publish a post (or a video) on a connected account: Instagram, YouTube, TikTok, X, Threads, LinkedIn, Facebook (a Page) or Skool. Name the account with account_id (from channels.list), or name only the channel when the workspace has one account there. What a post may carry differs by channel and the answer says what was refused: YouTube and TikTok take one video, Instagram one image, one video (a Reel) or 2-10 images (a carousel), X up to 4 media, LinkedIn one image, Facebook text with a link, up to 10 images or one video. Publish only when the user explicitly asks for this post: it is public and cannot be taken back. A failure of type outcome_unknown may already be live: check before publishing again.

Input Schema

NameRequiredDescriptionDefault
textNoThe post's text: a caption, a description, a tweet, a post body.
titleNoA title, for channels whose posts have one (YouTube, Skool; TikTok uses text).
channelNoThe channel, when account_id is omitted and the workspace has one account on it (instagram, youtube, tiktok, x, threads, linkedin, facebook, skool).
optionsNoThe channel's own settings, e.g. YouTube {tags, category_id, made_for_kids}, TikTok {disable_comment, disable_duet, disable_stitch, brand_content_toggle, brand_organic_toggle}, Instagram {alt_text, location_id, share_to_feed}, Threads {reply_control, alt_text}, Facebook {link, scheduled_at (ISO 8601 with offset, 10 minutes to 30 days ahead)}. An option the channel does not have is refused.
audienceNoWho sees it. OMIT for the channel's default. YouTube: public, unlisted, private; TikTok: public, friends, followers, private; LinkedIn: public, connections.
reply_toNoA post of this account to answer (a thread of posts on X or Threads).
account_idNoThe account that publishes (its id from channels.list).
destinationNoWhere inside the account it goes, when the channel has places: a Skool community id.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
media_file_idsNoWorkspace files to attach, in order (ids from files).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / channel / description
      Previous value: -"The channel, when account_id is omitted and the workspace has one account on it (instagram, youtube, tiktok, x, threads, linkedin, skool)."New value: +"The channel, when account_id is omitted and the workspace has one account on it (instagram, youtube, tiktok, x, threads, linkedin, facebook, skool)."
    • changedInput schema / properties / options / description
      Previous value: -"The channel's own settings, e.g. YouTube {tags, category_id, made_for_kids}, TikTok {disable_comment, disable_duet, disable_stitch, brand_content_toggle, brand_organic_toggle}, Instagram {alt_text, location_id, share_to_feed}, Threads {reply_control, alt_text}. An option the channel does not have is refused."New value: +"The channel's own settings, e.g. YouTube {tags, category_id, made_for_kids}, TikTok {disable_comment, disable_duet, disable_stitch, brand_content_toggle, brand_organic_toggle}, Instagram {alt_text, location_id, share_to_feed}, Threads {reply_control, alt_text}, Facebook {link, scheduled_at (ISO 8601 with offset, 10 minutes to 30 days ahead)}. An option the channel does not have is refused."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it discloses that publishing is public and irreversible, explains per-channel media limits and that unsupported options are refused, and warns that an outcome_unknown failure may already be live and should be checked before retrying. That is exactly the behavioral context an agent needs for a destructive, non-idempotent open-world operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite its length, every sentence carries operational information: channel selection, media constraints, refusal behavior, and retry safety. The purpose and channel list are front-loaded, and the most critical safety warning is placed last for emphasis.

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 10-parameter, nested-options publishing tool with no output schema, the description covers account targeting, per-channel payload rules, refusal reporting, destructive side effects, and partial-failure recovery. 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?

With 100% schema description coverage, the schema already documents each parameter, but the description adds cross-parameter meaning: account_id comes from channels.list, channel is the fallback, options are channel-specific, audience defaults by omission, and reply_to creates a thread. This materially supplements the schema rather than restating it.

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 and resource: 'Publish a post (or a video) on a connected account,' then names every supported channel. It clearly distinguishes the tool's scope from read/update siblings such as channels_list and youtube_update_video.

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 a strong gating condition: 'Publish only when the user explicitly asks for this post: it is public and cannot be taken back,' and explains how to choose between account_id and channel when the workspace has one account. It does not name explicit alternative tools for scheduling, drafting, or editing, but the when/when-not guidance is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All dialogbrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources