Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Find the creators already winning in a niche

find_creators

Scan TikTok, Instagram Reels and YouTube for a niche, rank real creators by median views, engagement and public contact info, so you can start outreach.

Instructions

Scan organic TikTok, Instagram Reels and YouTube for a niche across a few query variants, fold the posts into creators, and rank them on median views, engagement rate and how often they show up for that niche; the top rows get follower counts AND public contact info (an Instagram business email / phone / category, the bio link, an email in a TikTok bio) so outreach can start from the result. Real people, not AI actors — for influencer sourcing, UGC casting and partnership prospecting ("who should we send product to?"). About one credit per search call (platforms × queries, default 3 × 3) plus one per enriched profile; repeats inside 20 minutes are free. Then shortlist (save_to_swipefile), check a profile (instagram_profile / fetch_social_data), draft outreach (generate_text), or approve them for Partnership Ads (manage_meta_partnership_creator). marketplace:true also searches Instagram’s creator marketplace (Meta’s own creator directory: followers, badges, marketplace email) for the same niche and returns those rows beside the ranked list.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNocreators to return, 1–30 (default 12)
nicheYesproduct category, topic or hashtag — "calorie tracker app", "matcha", "#cleanbeauty"
enrichNoread follower counts for the top 6 (default true, ~1 credit each)
queriesNoquery variants per platform, 1–4 (default 3); each is a paid search call
platformsNodefault all three
marketplaceNoalso search Instagram’s creator marketplace (Meta’s own creator directory, free) for the same niche; needs the Meta connector
minAvgViewsNo
minEngagementNointeractions per view, 0–1 (0.05 = 5%)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.272
    • addedInput schema / properties / marketplace
      Added value: +{
+  "description": "also search Instagram’s creator marketplace (Meta’s own creator directory, free) for the same niche; needs the Meta connector",
+  "type": "boolean"
+}
  2. Addedv0.1.209

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, it discloses cost model (one credit per search call = platforms × queries, plus one per enriched profile), a 20-minute free-repeat caching window, enrichment scope (top 6, default), and the Meta connector prerequisite for marketplace:true — rich behavioral context the annotations do not carry.

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 scan/rank behavior and value, but the single dense paragraph is long and packs workflow, pricing, and marketplace details into run-on clauses. Every element is useful, but structure could be tighter.

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?

No output schema exists, yet the description specifies return content (ranked creators with median views, engagement rate, follower counts, and contact info). Combined with cost and workflow context, an agent has everything needed to call it correctly.

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 already 88%, so the schema documents most params. The description still adds the credit formula tying platforms and queries together, the enrich default/cost, and the marketplace connector dependency, going modestly beyond the schema text.

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 (scan/fold/rank) across named platforms and resources, and clearly distinguishes itself from list_creators and search_* siblings by describing aggregation into ranked creators. An agent knows exactly what this returns without opening the 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?

Explicitly frames the use cases (influencer sourcing, UGC casting, partnership prospecting) and names the downstream alternatives (save_to_swipefile, instagram_profile / fetch_social_data, generate_text, manage_meta_partnership_creator), routing the agent through the workflow.

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