AutoPoster AI

Create Post Draft

autoposter_draft_post

Creates a draft post for human review. If API key lacks direct publish, post is saved as pending_approval and notifications are sent to workspace approvers. Accepts mediaUrls (public URLs) or files (AI-generated images or uploaded files from chat up to 100MB). For large video files over 100MB, tell the user to provide a direct public file URL or use autoposter_get_media_upload_url.

Input Schema

TableJSON Schema

Name	Required	Description
`files`	No	Optional files generated in chat or uploaded by user to attach to the post.
`content`	Yes	Base text content of the post.
`mediaIds`	No	Optional list of existing media IDs from workspace media library (from autoposter_list_media).
`mediaUrls`	No	Optional public image or video URLs to attach (e.g. from autoposter_upload_media).
`accountIds`	Yes	List of account IDs from autoposter_list_accounts.
`platformContent`	No	Optional platform-specific content overrides (e.g. twitter, linkedin).

Output Schema

TableJSON Schema

Name	Required	Description
`message`	Yes	Status message indicating draft creation.
`draftPosts`	Yes	List of created draft posts per account.
`instructions`	No	Instructions for approving or viewing the draft.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "draftPosts": {
+      "description": "List of created draft posts per account.",
+      "items": {
+        "properties": {
+          "accountName": {
+            "description": "Target account name.",
+            "type": "string"
+          },
+          "id": {
+            "description": "Draft post ID.",
+            "type": "string"
+          },
+          "platform": {
+            "description": "Target social media platform.",
+            "type": "string"
+          },
+          "scheduledAt": {
+            "description": "Scheduled timestamp if any.",
+            "type": "string"
+          },
+          "status": {
+            "description": "Current post status (drafts or pending_approval).",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "platform",
+          "status"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "instructions": {
+      "description": "Instructions for approving or viewing the draft.",
+      "type": "string"
+    },
+    "message": {
+      "description": "Status message indicating draft creation.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "message",
+    "draftPosts"
+  ],
+  "type": "object"
+}

First observedOct 7, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the write/safety profile is already covered. The description adds genuine context beyond that: the pending_approval fallback, approver notifications, the 100MB file ceiling, and accepted media sources. It still doesn't say what happens to the draft afterward or mention auth requirements.

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?

Three tight sentences, front-loaded with the core action and followed by the approval behavior and the size-limit fallback. Every sentence carries actionable content, though the density of three separate concerns in one paragraph makes it slightly less scannable.

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?

With an output schema present, return values need not be described, and the description covers the approval workflow, media inputs, size limits and escalation path. It leaves minor gaps around account selection and the effect of platformContent, but nothing that would cause a misfire.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning for mediaUrls (public URLs) and files (AI-generated or chat-uploaded up to 100MB) that the schema alone does not convey. It adds nothing about accountIds, mediaIds, content, or platformContent beyond what the schema states.

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 ('Creates a draft post for human review'), and the 'draft ... for human review' framing implicitly separates it from the publish/schedule siblings. It does not name autoposter_publish_draft or autoposter_schedule_post explicitly, so sibling differentiation is inferential rather than stated.

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?

Gives clear conditions: when the API key lacks direct publish the post goes to pending_approval, and for media over 100MB it routes the agent to a public file URL or autoposter_get_media_upload_url. There is no explicit guidance on when to choose draft over schedule_post or publish_draft, so the routing is partial.

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

All AutoPoster AI 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?