Skip to main content
Glama

SocialGPT

by io.github.scrollmark
OverviewDiscussionsAdmin

Analyze a creator

analyze_creator

Analyze a public TikTok, YouTube, or Instagram creator's recent posts — adds them to your analysis library. Async — returns a job_id; poll get_analysis_status(job_id). Results then appear via list_creator_videos / get_creator. Rate limit: 10 calls/hour.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
platformYesTarget platform — instagram, tiktok, or youtube (case-insensitive).
usernameYesThe creator's public handle, e.g. 'natgeo' (no leading @).
post_limitNoHow many of the creator's recent posts to scrape + analyze (1–30, default 10; clamped).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteYes
job_idYes
statusYesAlways 'pending' at creation; poll the matching status tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • removedOutput schema / additionalProperties
      Removed value: -true
    • addedOutput schema / description
      Added value: +"Output of `analyze_creator` / `publish_post` — an async job was queued."
    • addedOutput schema / properties
      Added value: +{
+  "job_id": {
+    "type": "string"
+  },
+  "note": {
+    "type": "string"
+  },
+  "status": {
+    "description": "Always 'pending' at creation; poll the matching status tool.",
+    "type": "string"
+  }
+}
    • addedOutput schema / required
      Added value: +[
+  "job_id",
+  "status",
+  "note"
+]
  2. Changed3 schema fields changed
    • addedInput schema / properties / platform / description
      Added value: +"Target platform — instagram, tiktok, or youtube (case-insensitive)."
    • addedInput schema / properties / post_limit / description
      Added value: +"How many of the creator's recent posts to scrape + analyze (1–30, default 10; clamped)."
    • addedInput schema / properties / username / description
      Added value: +"The creator's public handle, e.g. 'natgeo' (no leading @)."
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Discloses mutation ('adds to library'), async behavior, and rate limit, which go beyond annotations. Annotations have readOnlyHint=false, consistent with mutation. No contradictions. Could elaborate on idempotency or duplicate handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, then async and polling details. Every word earns its place. No fluff.

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 parameters, annotations, output schema existence (not shown but assumed), and sibling tools, the description covers purpose, async flow, rate limits, and result retrieval. Complete for an async analysis tool.

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?

All three parameters have schema descriptions, so baseline is 3. Description repeats platform options and 'no leading @' already in schema, but adds 'case-insensitive' and mentions post_limit range (1–30) that is also in schema. No additional value beyond 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 it analyzes a creator's recent posts and adds them to the analysis library. It distinguishes from siblings like analyze_post (single post) and get_creator (just info) by specifying the scope and outcome.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly notes the asynchronous nature, how to poll with get_analysis_status, and where results appear (list_creator_videos / get_creator). Mentions rate limit (10 calls/hour). Lacks explicit 'when not to use' but provides clear next steps.

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

All SocialGPT 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