SocialGPT

Analyze a post

analyze_post

Analyze a single TikTok, YouTube, or Instagram post by URL — adds it to your library and runs deep video analysis. Returns immediately with the post's platform + post_id; deep analysis runs async (~30-60s). Then call get_video_analysis(platform, post_id) to read it — while it runs you get {"status": "pending"}, so wait ~20s and retry until the full result comes back ('pending' is expected, not a failure). Only posts within the creator's recent media (roughly their last ~75 posts) can be fetched. Rate limit: 30 calls/hour.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`post_url`	Yes	Full public URL of a single TikTok, YouTube, or Instagram post / reel / video.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	Yes
`post`	Yes	The post just queued by `analyze_post`.
`creator_id`	Yes
`ingest_job_id`	Yes	Creator-backfill job id; null unless a new creator was created.
`is_new_creator`	Yes
`analysis_status`	Yes	Deep-analysis job status at ingest time (e.g. 'pending').

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedJul 24, 2026

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / description

Added value: +"Output of `analyze_post`. Deep analysis runs async — poll\n`get_video_analysis(platform, post_id)`; when `is_new_creator` is true a\nbackfill job also runs (poll `get_analysis_status(ingest_job_id)`)."

addedOutput schema / properties

Added value: +{
+  "analysis_status": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Deep-analysis job status at ingest time (e.g. 'pending')."
+  },
+  "creator_id": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "ingest_job_id": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Creator-backfill job id; null unless a new creator was created."
+  },
+  "is_new_creator": {
+    "type": "boolean"
+  },
+  "note": {
+    "type": "string"
+  },
+  "post": {
+    "description": "The post just queued by `analyze_post`.",
+    "properties": {
+      "caption": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "creator_username": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Composite resource id ('<platform>:<post_id>') usable with `fetch`."
+      },
+      "platform": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "post_id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "The platform-native post id — pass to get_video_analysis."
+      }
+    },
+    "required": [
+      "id",
+      "platform",
+      "post_id",
+      "caption",
+      "creator_username"
+    ],
+    "type": "object"
+  }
+}

addedOutput schema / required

Added value: +[
+  "post",
+  "creator_id",
+  "is_new_creator",
+  "analysis_status",
+  "ingest_job_id",
+  "note"
+]

Changed1 schema field changedJun 24, 2026

addedInput schema / properties / post_url / description

Added value: +"Full public URL of a single TikTok, YouTube, or Instagram post / reel / video."

First observedJun 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Discloses that the tool mutates state (adds to library), runs async analysis with expected 'pending' status, and rate limits. Annotations already indicate non-read-only and non-destructive, and description adds significant context beyond annotations.

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?

Description is well-structured and front-loaded with key info. Every sentence adds value, though slightly verbose. Could be trimmed without losing clarity.

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?

Covers async behavior, retry logic, constraints (recent media), rate limits, and next steps. An output schema exists but description still explains immediate return and how to retrieve results, making it complete for agent use.

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% and schema parameter description is already clear. The main description reiterates the URL platforms but does not add new information beyond the schema.

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 clearly states the tool analyzes a single TikTok, YouTube, or Instagram post by URL, adds it to the library, and runs deep video analysis. It specifies the verb and resource, and distinguishes from siblings like analyze_creator.

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?

Provides explicit guidance: when to use (analyzing a post), what not to use (only recent ~75 posts), retry logic with get_video_analysis, and rate limit. Includes async behavior explanation.

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

All SocialGPT 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.