Socialync

get_top_posts

Read-only

Get the user's posts with engagement metrics, ranked by engagement or recency. Returns the same data as the Top Performing Posts and Recent Posts tables on the analytics page: views, likes, comments, shares, engagement rate, and a status that compares each post with this account's own usual on that platform (good = at least twice its usual, average = around its usual, below_usual = under half of it, viral = huge reach on any account). not_rated means there are fewer than 5 settled posts to compare with, the post is under 2 days old, or it is a YouTube post, which carries no status, rate or engagement total because YouTube's API policy does not allow metrics derived from its data. no_data means nothing has been collected for that post yet. Video posts on Instagram, Facebook and YouTube also carry a "watch" block with how people watched (average watch time in seconds, share held past the 3 second mark, skip rate, replays, follows gained); includeRetention=true adds the retention curve (t = position in the video 0..1, v = share of plays still watching) and YouTube traffic sources.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_top_posts"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No	"engagement" sorts by total engagement (top performers); "recent" sorts by post date (newest first)	engagement
`limit`	No	Number of posts to return
`platform`	No	Filter by a single platform or "all"	all
`minStatus`	No	Only return posts at or above this tier (e.g. "good" returns only viral and good posts). Posts that are not_rated or no_data are left out. "flop" is the old name for below_usual and still works.
`profileId`	No	The Socialync profile to report on. Call list_profiles to see authorized profiles. Omit to use the single/default authorized profile.
`includeRetention`	No	Add each video's retention curve (watch.retention, and for YouTube watch.relativeRetention where 0.5 is typical for similar-length videos) and YouTube traffic sources. Use it to find where viewers stopped watching; keep limit small, the curves are up to 50 points each.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 5, 2026

changedInput schema / properties / minStatus / description

Previous value: -"Only return posts at or above this performance tier (e.g. \"good\" returns only viral and good posts; matches the page's Top Performing filter)"New value: +"Only return posts at or above this tier (e.g. \"good\" returns only viral and good posts). Posts that are not_rated or no_data are left out. \"flop\" is the old name for below_usual and still works."

changedInput schema / properties / minStatus / enum

Previous value: -[
-  "flop",
-  "average",
-  "good",
-  "viral"
-]New value: +[
+  "below_usual",
+  "flop",
+  "average",
+  "good",
+  "viral"
+]

Changed1 schema field changedOct 26, 2026

addedInput schema / properties / includeRetention

Added value: +{
+  "default": false,
+  "description": "Add each video's retention curve (watch.retention, and for YouTube watch.relativeRetention where 0.5 is typical for similar-length videos) and YouTube traffic sources. Use it to find where viewers stopped watching; keep limit small, the curves are up to 50 points each.",
+  "type": "boolean"
+}

First observedOct 12, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/destructiveHint=false and a closed world, so the safety profile is covered; the description still adds a great deal of behavior beyond that. It defines every status tier with numeric thresholds, explains why not_rated occurs (fewer than 5 settled posts, post under 2 days, YouTube API policy) and what no_data means, and discloses that retention curves inflate payload size. It stops short of describing cost or ordering guarantees under ties.

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

Conciseness3/5

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

The purpose and the sort semantics are front-loaded, which is good, but the rest is one dense paragraph of chained clauses and parentheticals that is hard to scan. Nearly every sentence carries information, yet the YouTube API-policy aside and the inline status glossary push this well past what is needed to select and call the tool.

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 no output schema, the description carries the full burden of explaining what comes back, and it does: the metric list, the status vocabulary, the 'watch' block contents, and the conditional retention/traffic-source additions. Combined with fully documented parameters, an agent has everything required to call it correctly.

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%, so the schema already documents all six parameters including enum meanings, so the baseline is 3. The description does add some value on top: it spells out the status tiers used by minStatus and gives the structure of the retention curve (t = position 0..1, v = share of plays still watching, relativeRetention where 0.5 is typical), but most of this duplicates what the schema descriptions already state.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first clause gives a specific verb+resource+sort ('Get the user's posts with engagement metrics, ranked by engagement or recency') and maps the output to two known analytics tables. It does not, however, distinguish this from near-siblings like get_post_insights or get_post_history, so an agent must infer the split.

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

Usage Guidelines3/5

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

There is real usage guidance at the parameter level ('Use it to find where viewers stopped watching; keep limit small, the curves are up to 50 points each'), which is more than most tools give. But there is no when-to-use/when-not guidance relative to get_analytics, get_post_insights, or get_post_history, so selection between siblings is left to inference.

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

All Socialync 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.