Skip to main content
Glama

Create draft post

create_draft_post

Create a DRAFT post on a Flomixy Instagram, Threads, Facebook, LinkedIn, TikTok, Pinterest, YouTube, Bluesky, or Google Business Profile account. For YOUTUBE (a video; optional yt* options such as ytTitle, ytMadeForKids, ytPrivacyStatus): a draft may omit ytTitle/ytMadeForKids, but both are required before it can be scheduled. Address the target with channel + accountId (or the legacy instagramAccountId for Instagram only). The post is always subject to approval before it can be scheduled or published — it never goes live directly, no matter what this tool is called with. If the user wants a post with an image/video but gave no URL or media id, ask first which they prefer: (a) a public link, (a2) a file the AI itself produced: upload_media with contentBase64 (one file per call, up to 10 MB, no manual step), (b) upload via a Flomixy upload link (create_upload_link; with shell access curl the returned uploadEndpoint, no base64), (c) pick from the media library (list_media), (d) a stock photo (search_stock_photos, images only), (e) generate with AI: generate_image (images only, monthly quota), (f) no media, only if the network allows it (see get_channel_capabilities). If media is already provided, do not ask.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_draft_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
ytTagsNoYOUTUBE only: tags, 500 characters in total (maxYtTagsChars; commas count, a tag with a space costs 2 more).
captionNoPost caption. The limit depends on the channel (e.g. Instagram 2200, Threads 500, LinkedIn 3000 UTF-8 bytes; see get_channel_capabilities maxCaptionBytes).
channelNoPublishing channel, canonically UPPERCASE (e.g. INSTAGRAM); lowercase is accepted too. Use with accountId instead of instagramAccountId.
pinLinkNoPINTEREST only: destination link of the pin (http/https). The pin description has no clickable link, put the URL here.
ytTitleNoYOUTUBE only: video title, max 100 characters (maxYtTitleChars), no < or >. REQUIRED for a YOUTUBE target.
pinTitleNoPINTEREST only: pin title, max 100 characters (maxPinTitleChars).
postTypeNoPost format, canonically lowercase (image, carousel, reel, story); uppercase is accepted too. Defaults to image.
accountIdNoThe Flomixy account id for `channel`. Required for every channel except THREADS.
gbpCtaUrlNoGBP only: destination of the call-to-action button (http/https).
mediaUrlsNoMedia URLs for the post (http/https only).
gbpCtaTypeNoGBP only: call-to-action button. Every type except CALL needs gbpCtaUrl; CALL must not carry a URL. Ignored on OFFER.
mediaTypesNoMedia types, e.g. ["image"] or ["video"].
pinAltTextNoPINTEREST only: image alt text, max 500 characters (maxPinAltTextChars).
gbpEventEndNoGBP only: event/offer end, ISO 8601 WITH time zone; not before gbpEventStart.
gbpOfferUrlNoGBP only, OFFER: link to redeem the offer.
gbpPostKindNoGBP only: UPDATE (default), EVENT or OFFER. EVENT and OFFER REQUIRE gbpEventTitle, gbpEventStart and gbpEventEnd.
bskyAltTextsNoBLUESKY only: alt text per image, in the order of the images (max 2000 characters each, maxBskyAltTextChars).
ytCategoryIdNoYOUTUBE only: video category id, e.g. "22" (People & Blogs).
bskyReplyGateNoBLUESKY only: who may reply (threadgate), everyone when omitted.
gbpEventStartNoGBP only: event/offer start, ISO 8601 WITH time zone. Interpreted in the location's own time zone by Flomixy.
gbpEventTitleNoGBP only: event/offer title (EVENT and OFFER).
gbpOfferTermsNoGBP only, OFFER: terms and conditions.
ytMadeForKidsNoYOUTUBE only: "made for kids" declaration (COPPA). REQUIRED for a YOUTUBE target and has no default: ask the user, never guess.
gbpOfferCouponNoGBP only, OFFER: coupon code.
ytThumbnailUrlNoYOUTUBE only: custom thumbnail URL (JPEG/PNG, max 2 MB).
bskyLinkPreviewNoBLUESKY only: attach a link preview card for the first URL in the text (default true).
ytPrivacyStatusNoYOUTUBE only: visibility, public when omitted.
ytSyntheticMediaNoYOUTUBE only: the video contains altered or synthetic (AI-generated) realistic media.
bskyContentLabelsNoBLUESKY only: self-applied content labels.
bskyDisableQuotesNoBLUESKY only: forbid quote posts (postgate).
instagramAccountIdNoLegacy Instagram-only addressing. Prefer channel + accountId for any channel, including Instagram.
ytNotifySubscribersNoYOUTUBE only: notify subscribers about the upload (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the critical behavior: the post is a draft, requires approval, and never goes live regardless of arguments. It also notes the YouTube draft may omit ytTitle/ytMadeForKids but both are needed before scheduling. It does not say what the call returns (post id, status) or what validation failures look like, which is a real gap for a 32-parameter creation tool.

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?

Front-loaded with purpose, then YouTube caveat, then addressing, then approval, then the media decision tree — a sensible order. It is long and the inline (a)/(a2)/(b)... enumeration is awkward prose, and "no matter what this tool is called with" is vague, but nearly every sentence carries actionable content.

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 32-parameter, zero-annotation, no-output-schema tool, the description covers the two things an agent cannot infer from the schema: the draft/approval lifecycle and how to source media. The remaining gap is return-value behavior and error handling, which the agent would otherwise have to discover by calling.

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 adds meaning beyond it by explaining the addressing model (channel + accountId, with instagramAccountId as legacy Instagram-only) and by giving an operational decision tree for how mediaUrls/mediaTypes get populated. It does not explain the interplay of gbp* or bsky* option groups beyond what the schema already documents.

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 ("Create a DRAFT post") plus the full channel surface it covers. The phrase "always subject to approval before it can be scheduled or published — it never goes live directly" implicitly separates it from the publishing sibling create_post without needing 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?

Explicitly routes media handling: if media is already provided, do not ask; otherwise ask the user to choose among public link, upload_media, create_upload_link, list_media, search_stock_photos, generate_image, or no media, each with a named sibling and a stated condition. Also states the YOUTUBE draft-vs-scheduling rule for ytTitle/ytMadeForKids.

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