Skip to main content
Glama
Sign In

Postkey: Instagram DM Automation and Comment-to-DM

by pro.postkey
OverviewDiscussionsAdmin

Turn a DM automation on

postkey_publish_automation
Destructive

Postkey: Publishes a DM automation's draft and switches it on (also turns a paused one back on). From then on it SENDS DMs to real people who trigger it, and those messages cannot be taken back. If this connection must ask a person first (the default), nothing is switched on: the request waits in Approvals in Postkey, and the result has waiting_for_approval true, which is not an error: do not call it again or say it was sent. Refused plan_limit when the plan's automations switched on at once are used up, and needs_a_person for one that sends email or runs on the customer's own bot. Call postkey_preview_action first. To switch it off use postkey_pause_automation. An X reply automation always waits in Approvals, whatever this connection's setting; the person reads every reply there.

Input Schema

NameRequiredDescriptionDefault
preview_idNoOptional: the preview_id postkey_preview_action gave for exactly these arguments today (UTC). Approvals then shows the person that you showed them the preview. A preview_id that does not match is ignored, never refused.
automation_idYesThe automation id (a UUID) from postkey_list_automations or postkey_create_automation.

Output Schema

NameRequiredDescriptionDefault
okYesfalse: refused (isError; code, message, guide_topic, url); no change.
urlNoWhere a person opens it in Postkey.
sentNofalse while it waits for approval.
limitNoThe plan's limit on automations switched on at once.
statusNoThe automation's status now.
messageNoWhat happened.
accountsNoPresent when an account failed: ok, message.
live_nowNoAutomations switched on now.
warningsNoNotes from publishing.
request_idNoThe held request: read it with postkey_get_approval or postkey_list_waiting_for_approval. A post held in Posts > Approvals has none.
switched_onNotrue: it is live and sends DMs.
held_becauseNoWhy it waits on a direct connection.
automation_idNoThe automation id.
waiting_for_approvalNotrue: NOT sent; waits for a person in Approvals.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • 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."
  2. Changed3 schema fields changed
    • changedInput schema / properties / automation_id / description
      Previous value: -"The automation id."New value: +"The automation id (a UUID) from postkey_list_automations or postkey_create_automation."
    • changedInput schema / properties / preview_id / description
      Previous value: -"Optional: the preview_id postkey_preview_action gave for exactly these arguments. The person then sees in Approvals that you showed them the preview."New value: +"Optional: the preview_id postkey_preview_action gave for exactly these arguments today (UTC). Approvals then shows the person that you showed them the preview. A preview_id that does not match is ignored, never refused."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "accounts": {
+      "description": "Present when an account failed: ok, message.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "automation_id": {
+      "description": "The automation id.",
+      "type": "string"
+    },
+    "held_because": {
+      "description": "Why it waits on a direct connection.",
+      "type": "string"
+    },
+    "limit": {
+      "description": "The plan's limit on automations switched on at once.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "live_now": {
+      "description": "Automations switched on now.",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "message": {
+      "description": "What happened.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "false: refused (isError true; code, message, guide_topic, url), nothing changed.",
+      "type": "boolean"
+    },
+    "request_id": {
+      "description": "The held request: read it with postkey_get_approval or postkey_list_waiting_for_approval. A post held in Posts > Approvals has none.",
+      "type": "string"
+    },
+    "sent": {
+      "description": "false while it waits for approval.",
+      "type": "boolean"
+    },
+    "status": {
+      "description": "The automation's status now.",
+      "type": "string"
+    },
+    "switched_on": {
+      "description": "true: it is live and sends DMs.",
+      "type": "boolean"
+    },
+    "url": {
+      "description": "Where a person opens it in Postkey.",
+      "type": "string"
+    },
+    "waiting_for_approval": {
+      "description": "true: NOT sent; waits for a person in Approvals.",
+      "type": "boolean"
+    },
+    "warnings": {
+      "description": "Notes from publishing.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}
  3. First observed

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 openWorldHint=true, but the description goes well beyond them: it discloses that real DMs are sent and cannot be recalled, that waiting_for_approval=true is not an error and must not be retried, and that plan_limit and needs_a_person are refusal outcomes. The X reply automation caveat is behavior no annotation could convey.

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 irreversible-send warning and the preview prerequisite are front-loaded, and each subsequent sentence covers a distinct failure or approval case. It is dense but nearly every clause carries operational weight; a small amount of the approval wording could be tightened.

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, open-world mutation with an output schema already defined, the description covers the gaps that matter: irreversibility, the approval gate, retry hazards, and refusal codes. Nothing an agent needs in order to call this safely is missing.

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 description coverage is 100%, so both automation_id and preview_id are already fully documented including the UUID pattern and the 'ignored, never refused' preview_id rule. The description reinforces the preview workflow but adds no parameter-level detail beyond the schema, making 3 the appropriate 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?

The opening sentence names a specific verb and resource ('Publishes a DM automation's draft and switches it on') and adds the secondary case ('also turns a paused one back on'). This clearly distinguishes it from postkey_create_automation, postkey_pause_automation, and postkey_update_automation without needing the 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 ordering guidance ('Call postkey_preview_action first'), a named alternative for the inverse operation ('To switch it off use postkey_pause_automation'), and conditional branches for the approval path and refusal cases. An agent knows exactly when to call this and when to stop.

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 toolsInspect
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