PostNitro

Generate Carousel and Schedule It

postnitro_generate_and_schedule

Convenience tool: generates a post with AI (postType 'CAROUSEL' by default, 'IMAGE' for a single-image post, or 'VIDEO' for a video), waits for it to finish, then creates a scheduled post that attaches the resulting design. May take 30-180 seconds (longer for a rendered video).

templateId, brandId, presetId, and responseType are optional if saved via postnitro_set_defaults.

The design that gets attached is the completed carousel's design ID (result.designId from the generation output) — NOT the generation job ID. You normally don't set designId; it's resolved automatically. Pass designId only to attach a pre-existing design instead of the freshly generated one.

If scheduling fails after the carousel is already generated (e.g. an invalid platform-settings combination), this tool returns the generated designId so you can fix the inputs and retry with postnitro_create_scheduled_post — WITHOUT regenerating (which would burn credits again).

Provide the scheduling fields (status, scheduledAt, selectedAccounts, captions, and any required per-platform settings) just as you would for postnitro_create_scheduled_post.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes	'DRAFT' or 'SCHEDULED'
`brandId`	No	Brand ID (optional if saved via postnitro_set_defaults)
`designId`	No	Attach a pre-existing design instead of the freshly generated one. Leave unset to use the generated carousel's design.
`postType`	No	'CAROUSEL' (default) generates a multi-slide carousel; 'IMAGE' generates a single-image post; 'VIDEO' generates a video whose slides are its scenes. The rest of the request is identical, except VIDEO also accepts videoSettings and only supports responseType 'MP4' or 'DESIGN'.	CAROUSEL
`presetId`	No	AI preset ID (optional if saved via postnitro_set_defaults)
`templateId`	No	Template ID (optional if saved via postnitro_set_defaults)
`postContent`	No	Caption text keyed by platform. Required unless a designId is set; at least one key must be non-empty. Hashtags are extracted automatically.
`requestorId`	No	Optional custom tracking ID
`scheduledAt`	Yes	ISO-8601 datetime string. Must be in the future.
`aiGeneration`	Yes
`postSettings`	No	Video render settings, used when any resolved postType is 'reel'. Optional: when omitted, the API fills each field from the videoSettings the attached design was generated with, falling back to 30 seconds with no audio. Same shape as a VIDEO post's videoSettings.
`responseType`	No	Output format. 'DESIGN' (default) creates the design with no rendered file — fastest, and enough for scheduling/editing. Use 'PDF' or 'PNG' when you need a rendered file back, or 'MP4' for a rendered video (postType 'VIDEO' only). Optional if saved via postnitro_set_defaults.
`videoSettings`	No	Video render settings — postType 'VIDEO' only. Required when responseType is 'MP4'. Scheduling a reel reuses these automatically, so you usually don't also need postSettings.
`generateImages`	No	Optional AI image generation — include this object to enable it, omit it for no images. When included, `context` is required and you (the agent) must author it from the post. Best-effort: the post still COMPLETES if images fail or aren't permitted (free plan / exhausted AI-image quota); check the GENERATE_IMAGES step via postnitro_check_status. Requires a paid plan, consumes the org's AI-image quota (separate from post credits), and adds latency.
`selectedAccounts`	No	Social-account IDs to publish to (from postnitro_list_social_accounts)
`tiktokPostSettings`	No	Required when a TikTok account is selected AND a designId is set. When SCHEDULED: if isBrandedContent is true, at least one of isYourBrand/isThirdPartyBrand must be true, and isBrandedContent cannot be true with privacyLevel SELF_ONLY.
`threadsPostSettings`	No	Required when a Threads account is selected AND a designId is set
`linkedinPostSettings`	No	Required when a LinkedIn account is selected. A designId is required when status is SCHEDULED (text-only LinkedIn posts can only be drafts).
`instagramPostSettings`	No	Required when an Instagram account is selected AND a designId is set

Output Schema

TableJSON Schema

Name	Required	Description
`post`	Yes	A scheduled post or draft
`message`	Yes	Confirmation message
`success`	Yes
`designId`	Yes	The design attached to the scheduled post
`warnings`	No	Non-fatal issues worth surfacing to the user (e.g. AI image generation did not complete)
`embedPostId`	Yes	The generation/import job ID
`scheduledPostId`	Yes	ID of the created scheduled post

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 7, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description is highly transparent about side effects: it generates AI content, waits, attaches a design, schedules the post, may consume credits, and can fail during scheduling while still returning a designId to avoid regenerating. It also mentions latency (30-180 seconds), optional image generation behavior, and plan/quota implications. This matches the annotations (readOnlyHint false, destructiveHint false, 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?

The description is well-structured and front-loaded with a one-sentence summary, followed by clarifications about designId, failure retry, and scheduling fields. It is somewhat long and repeats concepts also present in the schema, but the complexity of the tool justifies the length and the prose is organized and scannable.

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?

The description provides sufficient context for what the tool does, how long it may take, what to do on failure, and how to supply required scheduling fields. Since the output schema is present, the lack of explicit return-value details is acceptable; the description still covers the important designId failure-return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers 95% of parameters, and the description adds meaningful detail beyond the schema: it clarifies designId's role, explains postSettings reuse for reels, gives instructions for generateImages.context, and elaborates on responseType and videoSettings. Even nested parameters benefit from extra context such as the LinkedIn document/carousel distinction and TikTok requirements.

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 clearly states the tool's purpose: it generates a post with AI, waits for completion, then creates a scheduled post with the resulting design. It also distinguishes itself as a 'convenience tool' that combines generation and scheduling, and references the related postnitro_create_scheduled_post for the scheduling portion.

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?

The description gives practical guidance on how to use the tool, including how to handle scheduling failures by retrying with postnitro_create_scheduled_post, and notes that scheduling fields should be provided exactly as they would be for that sibling tool. It could be more explicit about when to choose this over sequentially calling generate_and_wait and create_scheduled_post, but the convenience-tool framing makes the usage intent reasonably clear.

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

All PostNitro tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Most tools are clearly separated by verb and noun (generate_carousel vs generate_image vs generate_video, import_* vs generate_*). The generic convenience names like generate_and_wait and import_and_wait are slightly ambiguous, but their descriptions and the _wait/_schedule suffixes make them distinguishable.

Naming Consistency4/5

All tools share the postnitro_ prefix and snake_case verb-first convention. A few compound names (generate_and_schedule, import_and_wait) break the strict verb_noun pattern, but the convention is otherwise consistent and predictable.

Tool Count2/5

With 35 tools, the surface exceeds the rubric's 25+ 'too many' threshold. Many entries are convenience wrappers (_wait, _and_schedule) around the same core operations and could be consolidated to reduce overload.

Completeness4/5

The domain is well covered: generation, import, output retrieval, scheduling, brands, social accounts, audio, templates, presets, and defaults. Minor gaps remain (no delete_brand, no upload/connect for audio/social accounts), but those are largely external or non-critical.

Resources

Need Help?