postnext

Create a post draft

create_post_draft

Idempotent

Create a new draft post for a platform. Drafts are not auto-published. For an X or Threads thread, pass threadParts (one string per post, 2 to 25) instead of content; each post must fit the platform limit (X 280, or 25,000 for a paid X account; Threads 500). When the user has multiple connected channels for the same platform (e.g. three Twitter accounts), pass channelName (e.g. "@acme") to target a specific one — call list_connected_accounts first to see the available handles. You can also pass the account providerId (with or instead of channelName): it still identifies the account after its handle changes. Pass clientRequestId for idempotent retries within 5 minutes. For an Instagram draft with exactly one video in mediaUrls, pass instagramTrialReel ("auto" or "manual") to publish it as a trial reel shown to non-followers first; "auto" lets Instagram share it with followers if it performs well; the video URL must end in .mp4, .mov or .avi with no query string, which is how PostNext recognises a video. To give images alt text (an image description for screen readers), pass media instead of mediaUrls: [{ "url": "...", "alt": "..." }] with an optional type (IMAGE, VIDEO or GIF; detected from the URL when missing). Alt text limits: X and Instagram 1,000 characters, Bluesky 2,000, LinkedIn 300 (saved for LinkedIn but not sent to it yet). Alt text is ignored on video and GIF. Returns dashboardUrl — a clickable link to view/edit the draft in the PostNext dashboard.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`media`	No
`content`	No
`platform`	Yes
`mediaUrls`	No
`providerId`	No
`channelName`	No
`threadParts`	No
`clientRequestId`	No
`instagramTrialReel`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`postId`	Yes
`status`	Yes
`platform`	Yes
`createdAt`	No
`dashboardUrl`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

addedInput schema / properties / media

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "alt": {
+        "maxLength": 2000,
+        "type": "string"
+      },
+      "type": {
+        "enum": [
+          "IMAGE",
+          "VIDEO",
+          "GIF"
+        ],
+        "type": "string"
+      },
+      "url": {
+        "$ref": "#/properties/mediaUrls/items"
+      }
+    },
+    "required": [
+      "url"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "type": "array"
+}

Changed3 schema fields changedOct 6, 2026

changedInput schema / properties / content / maxLength
```
Previous value: -2200New value: +25000
```

addedInput schema / properties / threadParts

Added value: +{
+  "items": {
+    "maxLength": 25000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 25,
+  "minItems": 2,
+  "type": "array"
+}

changedInput schema / required

Previous value: -[
-  "platform",
-  "content"
-]New value: +[
+  "platform"
+]

Changed1 schema field changedOct 2, 2026
- removedOutput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
Changed1 schema field changedSep 29, 2026
- addedInput schema / properties / instagramTrialReel
```
Added value: +{
+  "enum": [
+    "auto",
+    "manual"
+  ],
+  "type": "string"
+}
```

Changed1 schema field changedSep 24, 2026

addedInput schema / properties / providerId

Added value: +{
+  "maxLength": 256,
+  "minLength": 1,
+  "type": "string"
+}

First observedSep 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that drafts are not auto-published, the 5-minute idempotency window (expanding on idempotentHint), per-platform content limits, alt-text handling per platform, and the dashboardUrl return. This is meaningful operational context an agent cannot get from the structured fields.

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?

Heavily front-loaded with the key constraint (drafts not auto-published) before parameter detail, and every sentence carries distinct information. It is dense and reads as one long block with many semicolons, which slightly hurts scannability, but little is wasted.

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?

Given a 9-parameter tool with 0% schema descriptions, an output schema, and annotations covering the safety profile, the description covers all parameters, the draft semantics, idempotency, and even the return value. Nothing an agent needs to invoke it correctly is missing.

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?

Schema description coverage is 0%, so the description must carry the full load, and it does: threadParts (2-25 items, per-post limits), channelName vs providerId semantics, clientRequestId idempotency, instagramTrialReel values, media object shape with alt/type, and platform-specific alt-text limits. Excellent compensation for the coverage gap.

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+resource (Create a new draft post) plus platform scope, and clearly distinguishes itself from siblings: it names list_connected_accounts as a prerequisite helper and frames drafts as non-publishing, implicitly routing to schedule_post.

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?

Rich conditional routing is provided for parameters (threadParts vs content, channelName vs providerId, instagramTrialReel conditions, media vs mediaUrls). It names list_connected_accounts to call first, but never explicitly contrasts this tool with siblings like schedule_post or update_post_draft for the 'when-not' side.

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

All postnext 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?