BulkPublish

Retry failed post

retry_post

Destructive

Retry publishing a failed or partially failed post. Only retries the platforms that failed, not the ones that already succeeded. Platforms in status 'unconfirmed' (the publish request may have reached the platform but its response was lost — the post may already be live) are NOT retried unless republish is true; if the post has unconfirmed platforms and no failed ones, the call fails with a 400 and code UNCONFIRMED_REQUIRES_REPUBLISH — ask the user to check the account on the platform, and only pass republish: true after they confirm the post is not live. Use this when a post failed on some platforms and the user wants to retry just those.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`postId`	Yes	The post ID to retry.
`republish`	No	Explicit opt-in to also retry platforms in status 'unconfirmed'. Their publish may have already gone through, so this can DUPLICATE the post — only pass true after the user has checked the account and confirmed the post is not live. Defaults to false.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No
`author`	No	Who wrote the post: { id, name, image }. Null when that account is gone.
`labels`	No
`status`	No	draft, scheduled, processing, published, partial or failed.
`content`	No
`approver`	No	Who approved it: { id, name, image }. Null unless approvalStatus is approved.
`assignee`	No	Who is expected to act on it next: { id, name, image }. Null when nobody is.
`timezone`	No
`createdAt`	No
`mediaFiles`	No
`publishedAt`	No
`scheduledAt`	No
`retriedCount`	No	How many destinations were retried.
`postPlatforms`	No
`approvalStatus`	No
`skippedMaxRetries`	No	Destinations skipped for hitting the retry ceiling.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 24, 2026

addedOutput schema / properties / approver

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Who approved it: { id, name, image }. Null unless approvalStatus is approved."
+}

addedOutput schema / properties / assignee

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Who is expected to act on it next: { id, name, image }. Null when nobody is."
+}

addedOutput schema / properties / author

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Who wrote the post: { id, name, image }. Null when that account is gone."
+}

Changed1 schema field changedSep 11, 2026

changedOutput schema / properties / mediaFiles / anyOf

Previous value: -[
-  {
-    "items": {
-      "additionalProperties": {},
-      "properties": {},
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "string"
+        },
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        }
+      ]
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedSep 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "approvalStatus": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "content": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "createdAt": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "id": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "labels": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "mediaFiles": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "postPlatforms": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "properties": {
+              "platform": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "status": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "publishedAt": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "retriedCount": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "How many destinations were retried."
+    },
+    "scheduledAt": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "skippedMaxRetries": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Destinations skipped for hitting the retry ceiling."
+    },
+    "status": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "draft, scheduled, processing, published, partial or failed."
+    },
+    "timezone": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

First observedSep 3, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag destructive and non-idempotent behavior, but the description adds critical context: it explains that only failed platforms are retried, that unconfirmed platforms are excluded unless republish=true, and that using republish can duplicate posts. It also discloses the exact error behavior (400 with code UNCONFIRMED_REQUIRES_REPUBLISH) and instructs how to handle it. This goes well beyond the annotations and is essential for safe invocation.

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 description is thorough and slightly long, but every sentence contributes necessary details: purpose, platform scoping, unconfirmed handling, error guidance, and usage condition. It is front-loaded with the core action and then elaborates logically. No redundancy is present; it earns its length, though it could be trimmed slightly without losing value.

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 the tool's complexity (subtle platform statuses, error handling, user interaction) and the presence of an output schema, the description covers everything an agent needs: purpose, scope, parameter semantics, error behavior, and actionable guidance. The output schema handles return values, so no gaps are apparent. This is a complete, self-sufficient description.

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 both parameters are documented. The description adds significant meaning for republish: clarifying the exact condition for passing true (after user confirmation), the risk of duplication, and the error scenario. It also reinforces the purpose of postId. While the baseline for full schema coverage is 3, the added semantic depth for republish justifies a 4.

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 description opens with a specific verb and resource: 'Retry publishing a failed or partially failed post.' It immediately clarifies scope by stating it only retries failed platforms, not successful ones, which distinguishes it clearly from sibling tools like create_post or publish_post. The purpose is unmistakable and precise.

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?

The description explicitly states when to use the tool: 'Use this when a post failed on some platforms and the user wants to retry just those.' It also provides detailed conditions for the republish parameter, explains the UNCONFIRMED_REQUIRES_REPUBLISH error case, and advises how to interact with the user. This is exemplary usage guidance, including both when-to-use and when-not-to.

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

All BulkPublish 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?