Viral Manager

list_discovery_posts

Read-only

List posts from Discovery: Viral Manager's own catalogue of viral Instagram Reels and TikTok videos from curated accounts across niches (last 60 days), the same feed as the app's Discovery page. Not limited to the user's watchlist. Returns the posts with their thumbnails inline (set thumbnails false for text only). By default the niches the user hid on the Discovery page stay hidden; pass niche to read one niche (free text, e.g. 'fitness'), the response lists the available niches. multiplier is the virality multiplier shown on the card (write it as x22.4, nothing else). When presenting posts, always include each post's url. A post's analyzed_post_id (when the user already analyzed it) works with get_post_analysis; otherwise analyze_post_url with its url analyzes it. get_post_preview shows one post larger.

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": "list_discovery_posts"
  }
}

Input Schema

Name	Required	Description	Default
`days`	No	Only posts published in the last N days
`sort`	No	'page' = the Discovery page order (posts of the last 7 days by virality first, then day by day), 'multiplier' = highest multiplier first, 'recent' = newest first	page
`limit`	No	Number of posts to return (max 30)
`niche`	No	Only this niche (free text, matched against the niche names, e.g. 'fitness', 'business', 'nsfw'). Overrides the niches the user hid.
`offset`	No	Pagination offset
`thumbnails`	No	Return each post's thumbnail inline as an image (small, ~320 px wide)
`min_multiplier`	No	Only posts with at least this virality multiplier

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond readOnlyHint/openWorldHint, the description discloses real behavior: a 60-day data window, that hidden niches stay hidden by default and `niche` overrides them, that the response lists available niches, and that thumbnails are inline by default and can be disabled. It also gives output-presentation obligations (always include each post's url, write multiplier as x22.4), which the annotations cannot convey.

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?

Purpose and scope are front-loaded, and nearly every sentence carries actionable content (routing, defaults, formatting rules). It is a dense single block, though, with presentation instructions interleaved with data-scope facts; light structural separation would make it easier to scan without losing information.

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?

For a 7-parameter read tool with no output schema, the description covers the data source, time window, default filtering, return shape (posts with inline thumbnails, niche list), and the follow-up path for analysis or preview. Nothing an agent needs to call and correctly present results is missing.

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 the schema already defines days, sort, limit, offset, and min_multiplier, and the description wisely does not repeat them. It does add meaning the schema lacks: `niche` is free text matched against niche names and overrides hidden niches, and `thumbnails=false` yields text only. The presentation rule for multiplier is helpful but concerns output, not a parameter, so it doesn't fully lift this above 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 concrete verb+resource ("List posts from Discovery") and immediately defines the scope: Viral Manager's curated catalogue of viral Reels/TikToks, last 60 days, same as the app's Discovery page, and explicitly "not limited to the user's watchlist." It also names three sibling tools (get_post_analysis, analyze_post_url, get_post_preview) with their distinct roles, so an agent can separate this from related tools without opening schemas.

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?

It routes the agent explicitly: use get_post_analysis when an analyzed_post_id exists, analyze_post_url with the post's url otherwise, and get_post_preview to show a single post larger. It also states the default niche-hiding behavior and when to pass `niche` to read a specific one. This is explicit when-to-use and when-to-use-something-else guidance.

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

All Viral Manager 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?