Semantic discovery search for influencers/content creators using natural-language queries.
Use this only when the user asks to discover creators by topic, audience, geography,
niche, content style, or campaign criteria (e.g., "fitness creators in NYC", "vegan
recipe creators with high engagement", "tech reviewers who cover phones"). The query
is matched against creator profiles, extracted facts, and visual style via hybrid
vector search.
Do not use this for exact handles, usernames, or known creator names. If the user gives
a specific platform and handle (for example "@niickjackson on Instagram"), use
`get_profile` first. For rough name/handle lookup, use `search_creators`. For
multiple known handles, use `lookup_profiles`. Semantic search can return lookalike
or topical matches and is allowed to miss an exact username.
Examples:
- User: "Find news creators with 1M+ followers" -> use this tool.
- User: "Find creators in LA who make cinematic travel videos" -> use this tool.
- User: "Pull @niickjackson on Instagram" -> use `get_profile`, not this tool.
- User: "Is @niickjackson a fit for Pixel?" -> use `get_profile` first, optionally
`get_posts`, then `match_creators`.
Returns a ranked list of creators (id, platform, username, follower count, engagement
rate, top categories, evidence facts). Use the flat follower, engagement-rate, and
verified fields to constrain results when the user gives concrete numeric constraints.
Use `find_lookalike_creators` instead when you want creators SIMILAR to known ones.
Use `match_creators` when you want to SCORE specific creators against a brief.
