Skip to main content
Glama
Hermoso

Hermoso

Official

Top posts about any topic, brand or product

search_posts

Find the top-viewed organic TikTok, Instagram Reels and YouTube posts about a brand, product or hashtag in one ranked call, so you can read audience hooks and pick clips to clone.

Instructions

The POSTS people make ABOUT a subject — a brand ("liquid death"), a product, a hobby ("coffee"), a hashtag ("#homecafe") — from whoever posted them, across organic TikTok, Instagram Reels and YouTube in ONE call, ranked by views. Not the brand's own ads (search_meta_ads / research_ads) and not the people (find_creators folds these same posts into creators): use it to see what is actually being posted and watched about a subject, to find clips worth cloning (clone_video), and to read the hooks and angles an audience already responds to. About one credit per platform searched (one query each by default; queries adds "best X" / "X review" / #tag variants, each a paid call); repeats inside 20 minutes are free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic": "<topic>"
    },
    "name": "search_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoposts per platform, 1–60 (default 24)
topicYessubject, brand, product or hashtag — "liquid death", "coffee", "#homecafe"
queriesNoquery variants per platform, 1–4 (default 1); each is a paid search call
get_costNotrue: return the price only; nothing runs or bills
platformsNodefault all three
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.1.256
    • changedInput schema / properties / topic / description
      Previous value: -"subject, brand, product or hashtag — \"higgsfield\", \"coffee\", \"#homecafe\""New value: +"subject, brand, product or hashtag — \"liquid death\", \"coffee\", \"#homecafe\""
  3. Addedv0.1.249

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, openWorldHint=true and destructiveHint=false; the description adds the credit model (one credit per platform, `queries` variants each a paid call, repeats within 20 minutes free), which is exactly the kind of billing behavior annotations cannot convey. It stops short of describing pagination or the exact return shape, so not a full 5.

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?

Front-loaded with the core definition before the routing exclusions and cost note, and every clause carries information. The parentheticals stack up (example brands, hashtags, cost caveats), making it denser than ideal, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter search tool with no output schema, it covers scope, platform coverage, ranking signal (views), cost and dedupe window — enough to call correctly. It does not describe the shape of returned post records or how ranked results are paginated, a minor gap given there is no output schema to lean on.

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 baseline is 3, but the description genuinely extends the schema by explaining what `queries` variants are ("best X" / "X review" / #tag) and that each is a separately billed call. `limit`, `platforms` and `get_cost` are left entirely to the schema, which is acceptable given full coverage.

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?

States a specific verb and resource — posts people make about a subject across TikTok, Instagram Reels and YouTube, ranked by views — and immediately contrasts it with the two things it is not: brand ads (search_meta_ads / research_ads) and creators (find_creators). An agent can distinguish it from every named sibling without opening a schema.

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?

Gives explicit when-to-use cases (see what is being posted and watched, find clips worth cloning via clone_video, read hooks and angles) plus explicit exclusions routing to search_meta_ads, research_ads and find_creators. Both the positive and negative routing conditions are stated.

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

Deploy Server

Other Tools