Skip to main content
Glama

Create, schedule or publish a post

create_post

Create a post for one or more social accounts. Leave scheduledFor and publishNow empty to save a draft (optionally with a suggestedFor date the person will see when reviewing it); set scheduledFor to schedule; set publishNow to publish immediately. If the organization requires approval and the connected person cannot approve, a scheduled or immediate post is created PENDING APPROVAL instead (status PENDING_APPROVAL) and goes out once someone approves it. Validates each network before sending, so a rejected post comes back as an explained error instead of a silent failure. Note for comment-to-DM automations set to "next post": only a real publication claims them — a draft never does, and a scheduled post only when its time arrives and it actually goes out.

Input Schema

NameRequiredDescriptionDefault
altTextNoAccessibility alt text per image, keyed by its URL in mediaUrls: {"https://…/a.jpg":"A dog on a red sofa"}. Applied on Instagram feed, Facebook, Threads, X (max 1000), LinkedIn, Bluesky and Pinterest (max 500); ignored elsewhere. Write it for every image you attach — a post without alt text is unreadable to screen readers, and several networks rank it.
contentYesMain copy of the post.
useQueueNoSchedule in the next free slot of the organization's posting queue.
mediaUrlsNoPublic https URLs of images/videos to attach. THE ORDER MATTERS: it is the carousel order the reader swipes through, and the first one is the cover — the image that shows in the profile grid. Get them from generate_image, generate_video (via get_media_job), upload_media (for a file on the user's machine), import_media (for a url that is already public) or list_library_media.
accountIdsYesIgnix account ids from list_accounts.
publishNowNoPublish immediately.
aiGeneratedNoSet true only when the person wants the AI label: the post goes out with each network's AI label (Instagram, X, YouTube, TikTok video). It is their choice; when the media was generated or altered with AI (generated people, a person put into a video from a photo, a synthetic voice), ask them once whether they want it.
workspaceIdNoWorkspace to work on (an id from list_workspaces). Not needed when this connection is tied to one workspace, or when you pass an account: the account's workspace is used.
scheduledForNoWhen to publish. ISO 8601. Without a timezone ('2026-08-05T14:00') it is the organization's local time.
suggestedForNoDrafts only: a PROPOSED date (ISO 8601) shown when the person reviews the draft. It does not schedule anything; ignored if scheduledFor or publishNow is set.
idempotencyKeyNoOptional. A unique id for this action (16-128 chars: letters, digits, _ : . -). If you are unsure whether a call went through (timeout, network error), repeat it with the SAME idempotencyKey and the same arguments: you get the original result and nothing is done twice.
networkOptionsNoNetwork-specific options keyed by platform: first comment, collaborators, cover image, privacy, board, flair, TikTok consent… e.g. {"instagram":{"firstComment":"…","collaborators":"user1,user2"},"youtube":{"visibility":"public"},"pinterest":{"boardId":"…"}}. Call get_network_options for the EXACT list each network accepts, with types, accepted values and which ones are required.
perNetworkTextNoDifferent copy per network, keyed by platform, e.g. {"x":"short version","linkedin":"long version"}. Networks not listed use the main content.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / aiGenerated / description
      Previous value: -"Set true when the media was generated or altered with AI (realistic generated people, a person put into a video from a photo, a synthetic voice): the post goes out with each network's AI label (Instagram, X, YouTube, TikTok video). Images and videos made with Ignix's own generate_image / generate_video are labelled automatically."New value: +"Set true only when the person wants the AI label: the post goes out with each network's AI label (Instagram, X, YouTube, TikTok video). It is their choice; when the media was generated or altered with AI (generated people, a person put into a video from a photo, a synthetic voice), ask them once whether they want it."
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the PENDING_APPROVAL outcome and who can approve, that each network is validated before sending and failures surface as explained errors, and the subtle comment-to-DM claim semantics (draft never claims, scheduled only when it actually publishes). These are exactly the non-obvious behaviors an agent needs.

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?

Mode selection is front-loaded in the first two sentences, then approval, validation, and the automation caveat. Every sentence carries information, though the final comment-to-DM note is narrow enough that it slightly lengthens an already dense paragraph.

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 a 13-parameter mutation tool with nested objects and no output schema, the description covers mode selection, approval side effects, validation errors, and idempotency is handled in-schema. It does not say what a successful call returns (post id/status), which is the main remaining gap given there is no output schema.

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 explaining the interaction between scheduledFor, publishNow and suggestedFor (draft-only proposal, ignored when the others are set) — semantics not obvious from individual field docs. Remaining params are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create a post for one or more social accounts') and the title clarifies it also schedules/publishes. An agent can tell what it does, but the description never names its closest sibling (schedule_post) or explains why this tool already covers scheduling, leaving a small ambiguity against a very large sibling set.

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?

Explicitly maps parameter states to outcomes: empty scheduledFor/publishNow means draft, scheduledFor means schedule, publishNow means immediate. That is clear when-to-use guidance for the three modes. It stops short of routing the agent to alternatives like schedule_post, bulk_create_posts, update_post, or validate_post when those would be more appropriate.

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