Postkey: Instagram DM Automation and Comment-to-DM

Delete a draft post

postkey_delete_post

Destructive

Postkey: Deletes a post that was never sent: a draft kept in Postkey, or a post that waits for approval. It is gone from Postkey for good; the Library files it used stay in the Library. A scheduled post, or one already sent to the platform as a draft (detail_status draft_created), is refused scheduled: unschedule it first (postkey_unschedule_post), and a post that went out, even in part, cannot be deleted. Only when the person asks for it.

Input Schema

Name	Required	Description	Default
`post_id`	Yes	The post id (a UUID) from postkey_list_posts or postkey_create_post.

Output Schema

Name	Required	Description
`ok`	Yes	false: refused (isError; code, message, guide_topic, url); no change.
`note`	No	Its Library files stay.
`deleted`	No	true: the post is gone.
`post_id`	No	The post id.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedOutput schema / properties / ok / description

Previous value: -"false: refused (isError true; code, message, guide_topic, url), nothing changed."New value: +"false: refused (isError; code, message, guide_topic, url); no change."

Changed2 schema fields changedOct 24, 2026

changedInput schema / properties / post_id / description

Previous value: -"The post id."New value: +"The post id (a UUID) from postkey_list_posts or postkey_create_post."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "deleted": {
+      "description": "true: the post is gone.",
+      "type": "boolean"
+    },
+    "note": {
+      "description": "Its Library files stay.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "false: refused (isError true; code, message, guide_topic, url), nothing changed.",
+      "type": "boolean"
+    },
+    "post_id": {
+      "description": "The post id.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, and the description goes well beyond that by disclosing irreversibility ('gone from Postkey for good') and the side effect that Library media files are retained rather than deleted. It also names the exact refusal states and the recovery path, which annotations cannot express.

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 the definition before the exception paths, and nearly every clause carries new information (state exclusions, sibling reference, side effect, consent). It is a single dense semicolon-chained paragraph that could be split for scanability, which keeps it just short of ideal.

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 destructive one-parameter mutation with an output schema defined separately, the description covers everything an agent needs: what is destroyed, what survives, which states are refused, and which sibling tool to use instead. No return-value explanation is needed given the output schema.

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

Parameters3/5

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

Schema coverage is 100% for the single post_id parameter, including the UUID pattern and where to obtain it, so the description need not restate it. The description adds no parameter-level detail, leaving the schema to carry that load – the correct baseline.

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 (Deletes) and a narrowly scoped resource (a post that was never sent: a Postkey draft or a post awaiting approval). This distinguishes it immediately from sibling postkey_unschedule_post and postkey_update_post without opening any 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?

Explicit when-not conditions are given per state: scheduled posts are refused and must be unscheduled via postkey_unschedule_post first, posts already sent to the platform as a draft (detail_status draft_created) are refused, and fully sent posts cannot be deleted at all. It also adds a consent gate – 'Only when the person asks for it' – which resolves the ambiguity about proactive deletion.

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

All Postkey: Instagram DM Automation and Comment-to-DM 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?