PostNitro

by ai.postnitro.mcp

Overview Discussions Admin

Import Custom Carousel

postnitro_import_carousel

Create a carousel by importing your own slide content.

IMPORTANT: Call postnitro_get_import_template FIRST to see the exact slide structure and rules.

templateId, brandId, and responseType are optional if you've saved defaults via postnitro_set_defaults.

Strict rules (violations will cause errors):

First slide MUST be type "starting_slide" (exactly 1)
Middle slides MUST be type "body_slide" (at least 1)
Last slide MUST be type "ending_slide" (exactly 1)
Infographic columnCount must not exceed 3
When columnDisplay is "cycle", put ALL data in the FIRST columnData entry only
Setting layoutType "infographic" replaces the image field

Minimal example: slides: [ { type: "starting_slide", heading: "Welcome!", description: "Intro", cta_button: "Swipe →" }, { type: "body_slide", heading: "Key Point", description: "Details here" }, { type: "ending_slide", heading: "Thanks!", cta_button: "Learn More" } ]

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": {
      "slides": "<slides>"
    },
    "name": "postnitro_import_carousel"
  }
}

Input Schema

Name	Required	Description
`slides`	Yes	Array of slides
`brandId`	No	Brand ID (optional if saved via postnitro_set_defaults)
`templateId`	No	Template ID (optional if saved via postnitro_set_defaults)
`requestorId`	No	Optional custom tracking ID
`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. Optional if saved via postnitro_set_defaults.
`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.
`idempotencyKey`	No	Optional key that makes this call safe to retry. Generate a new one (e.g. a UUID) for each new action. If the call times out, fails with a network or 5xx error, or you are unsure it went through, call again with the SAME key and the same arguments: PostNitro returns the first call's result instead of creating a second post, charging credits again or scheduling a duplicate. Only a successful call is remembered, so after an error you can fix the arguments and retry with the same key; reusing a successful call's key with different arguments is rejected (422).

Output Schema

Name	Required	Description
`status`	Yes	Initial job status ('PENDING')
`message`	No	Message returned by the PostNitro API
`success`	Yes	True when the job was accepted
`nextStep`	Yes	The suggested follow-up call
`warnings`	No	Non-fatal issues worth surfacing to the user (e.g. AI image generation did not complete)
`embedPostId`	Yes	Generation-job ID — pass to postnitro_check_status, then postnitro_get_output
`usedDefaults`	Yes	The values actually applied — explicit arguments, saved defaults, or an auto-selected sole candidate

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 1, 2026

addedInput schema / properties / idempotencyKey

Added value: +{
+  "description": "Optional key that makes this call safe to retry. Generate a new one (e.g. a UUID) for each new action. If the call times out, fails with a network or 5xx error, or you are unsure it went through, call again with the SAME key and the same arguments: PostNitro returns the first call's result instead of creating a second post, charging credits again or scheduling a duplicate. Only a successful call is remembered, so after an error you can fix the arguments and retry with the same key; reusing a successful call's key with different arguments is rejected (422).",
+  "pattern": "^[\\x21-\\x7E]{1,200}$",
+  "type": "string"
+}

First observedSep 7, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare it is not read-only, not destructive, not idempotent; the description adds real value beyond that by disclosing that strict structural rules are enforced and that violations cause errors. It does not mention credit consumption or how the tool relates to the scheduling variants, leaving some behavioral context to the schema.

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?

Well front-loaded: purpose, then the prerequisite call, then numbered rules, then a compact example. A couple of the numbered rules (columnCount ≤ 3, columnDisplay cycle) restate what the schema descriptions already say, which is minor duplication in an otherwise tight definition.

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 deeply nested 7-parameter tool with an output schema and full schema coverage, the description supplies the two things structured fields can't: the mandatory template-discovery step and a concrete valid slide array. An agent can construct a correct call from this plus the 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 goes beyond by adding ordering semantics for the slide array (exactly one starting_slide, at least one body_slide, exactly one ending_slide) and the columnDisplay "cycle" data-placement rule, plus a worked example. It still leaves the top-level optional params (requestorId, idempotencyKey) 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 carousel by importing your own slide content"), and the word "importing" implicitly separates it from postnitro_generate_carousel. However, it never clarifies how it differs from postnitro_import_and_schedule or postnitro_import_and_wait, which are the closest siblings by name.

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?

Strong operational guidance: an explicit prerequisite ("Call postnitro_get_import_template FIRST") and the note that templateId/brandId/responseType are optional when defaults are saved. What's missing is any statement of when to choose this tool over import_and_schedule/import_and_wait.

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

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

Need Help?