SocialGPT

Account engagement metrics

get_account_metrics

Read-only

Get per-platform engagement (views / likes / comments / shares) as a time series over the trailing window_days (default 28, up to 365). Omit account_id to aggregate across all connected accounts, or pass one from list_accounts; optionally filter to a single platform. post_limit (≤100) fixes how many recent posts form the baseline. granularity buckets the series server-side ('daily' default, 'weekly', or 'raw' for every scrape). Read series (a clean per-platform list of typed points) — metrics is the legacy column/data matrix kept for back-compat. NB: follower counts here are latest-only; for audience growth over time use get_follower_history.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`platform`	No	Optional platform filter — instagram, tiktok, or youtube (case-insensitive). Omit to span all connected platforms.
`account_id`	No	A connected account_id from list_accounts. Omit to aggregate across all your accounts.
`post_limit`	No	How many recent posts form the baseline (1–100, default 20; clamped).
`granularity`	No	Time-series bucketing: 'daily' (default), 'weekly', or 'raw' (every scrape).	daily
`window_days`	No	Trailing window in days (1–365, default 28; out-of-range values are clamped).

Output Schema

TableJSON Schema

Name	Required	Description
`reason`	No	Present only when the requested account_id could not be resolved.
`series`	Yes	Per-platform typed time series.
`metrics`	Yes	Legacy per-platform {columns, data} matrix (back-compat).
`platform`	Yes
`platforms`	Yes
`account_id`	Yes	The account_id the caller passed (null = all accounts).
`post_limit`	Yes
`granularity`	Yes
`window_days`	Yes

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 `get_account_metrics`. `reason`='account_not_found' appears\nonly when the requested account_id resolved to none of the caller's\naccounts (then platforms/series/metrics are empty)."

addedOutput schema / properties

Added value: +{
+  "account_id": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "The account_id the caller passed (null = all accounts)."
+  },
+  "granularity": {
+    "enum": [
+      "daily",
+      "weekly",
+      "raw"
+    ],
+    "type": "string"
+  },
+  "metrics": {
+    "additionalProperties": true,
+    "description": "Legacy per-platform {columns, data} matrix (back-compat).",
+    "type": "object"
+  },
+  "platform": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "platforms": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "post_limit": {
+    "type": "integer"
+  },
+  "reason": {
+    "anyOf": [
+      {
+        "const": "account_not_found",
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Present only when the requested account_id could not be resolved."
+  },
+  "series": {
+    "additionalProperties": {
+      "items": {
+        "additionalProperties": true,
+        "description": "One time-series point. Metric columns (views, like_count,\nfollower_count, ...) are carried as additional properties; `bucket` is\npresent only for 'daily'/'weekly' granularity.",
+        "properties": {
+          "bucket": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "description": "Bucket label (ISO date or ISO year-week); absent for granularity='raw'."
+          },
+          "timestamp": {
+            "anyOf": [
+              {
+                "format": "date-time",
+                "type": "string"
+              },
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "description": "Snapshot time of this point."
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "description": "Per-platform typed time series.",
+    "type": "object"
+  },
+  "window_days": {
+    "type": "integer"
+  }
+}

addedOutput schema / required

Added value: +[
+  "account_id",
+  "platform",
+  "window_days",
+  "post_limit",
+  "granularity",
+  "platforms",
+  "series",
+  "metrics"
+]

Changed5 schema fields changedJun 24, 2026

addedInput schema / properties / account_id / description

Added value: +"A connected account_id from list_accounts. Omit to aggregate across all your accounts."

addedInput schema / properties / granularity / description

Added value: +"Time-series bucketing: 'daily' (default), 'weekly', or 'raw' (every scrape)."

addedInput schema / properties / platform / description

Added value: +"Optional platform filter — instagram, tiktok, or youtube (case-insensitive). Omit to span all connected platforms."

addedInput schema / properties / post_limit / description

Added value: +"How many recent posts form the baseline (1–100, default 20; clamped)."

addedInput schema / properties / window_days / description

Added value: +"Trailing window in days (1–365, default 28; out-of-range values are clamped)."

Changed1 schema field changedJun 18, 2026

addedInput schema / properties / granularity

Added value: +{
+  "default": "daily",
+  "enum": [
+    "daily",
+    "weekly",
+    "raw"
+  ],
+  "type": "string"
+}

First observedJun 18, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations indicate readOnlyHint=true. Description adds that `series` is clean output while `metrics` is legacy, and explains parameter clamping. No contradiction with annotations; adds valuable behavioral context.

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 thorough but efficiently front-loaded with main action. Every sentence serves a purpose, though slightly lengthy. Could be trimmed marginally but remains clear.

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?

With output schema present, description still hints at output structure. Covers all aspects: purpose, parameters, alternatives, and behavioral notes. Sufficient for informed agent decision.

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 baseline is 3. Description adds meaning by explaining 'trailing window_days', granularity options, and that post_limit forms baseline. Provides context beyond schema without redundancy.

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 retrieves per-platform engagement metrics as a time series, specifying verb (get) and resource (account metrics). It distinguishes from sibling get_follower_history by noting follower counts are latest-only.

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 guidance on when to omit account_id for aggregation, filter by platform, and direct to use get_follower_history for audience growth over time. Provides clear usage context and alternatives.

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.