TikTok creator emails, YouTube channel contacts and video transcripts for AI assistants.
Scored across 3 tools
Each tool targets a clearly distinct resource and action: TikTok creator discovery, YouTube channel email resolution, and cross-platform video transcripts. There is no meaningful overlap between them; an agent can select the right tool from the name alone.
All three tools follow a clean verb_noun snake_case pattern (find_tiktok_creators, find_youtube_channel_emails, get_video_transcripts). The verb choices are appropriate and the naming is fully predictable.
Three tools is on the thin side but each is well-defined and earns its place in a lead-scraping workflow. It is slightly under-scoped rather than bloated, which is a reasonable trade-off for a focused server.
The server handles TikTok creator discovery, YouTube email resolution, and transcripts, but omits creator/lead discovery for Instagram and X even though transcripts span those platforms. The asymmetric platform coverage leaves notable gaps for a 'lead' toolset.
Find TikTok creators by keyword and return one row per creator: handle, bio, follower and like counts, plus any contact email, Instagram, YouTube or WhatsApp link the creator publishes. Billed to your Apify account at about $1 per 1,000 profiles.
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | Yes | Search terms, e.g. ["skincare routine", "home workouts"] | |
| maxResults | No | Maximum profiles to return. Keep this small while testing (default 20). | |
| maxFollowers | No | Maximum follower count | |
| minFollowers | No | Minimum follower count | |
| onlyWithEmail | No | Return only creators that publish a contact email |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose two real behavioral traits: the one-row-per-creator output shape and the pay-per-profile billing model, which is genuine cost/rate context. It stops short of covering auth prerequisites, pagination, or what happens when a keyword yields nothing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no filler. The return-value detail comes first and the billing caveat is packed into a short trailing clause that a cost-aware agent needs.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description's field enumeration is doing necessary work, and cost is disclosed too. It is nearly complete for a search tool, with only auth requirements and result-cap behavior left unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all five parameters including the keyword examples and follower bounds. The description only loosely echoes this via 'by keyword' and 'any contact email,' adding little beyond the structured fields, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Find) and resource (TikTok creators) and enumerates exactly what comes back per row: handle, bio, follower/like counts, and contact channels. This is clearly distinguishable from the YouTube and transcript siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives cost context for a run (~$1 per 1,000 profiles), which implicitly tells the agent to keep runs small, but it never states when to choose this tool over find_youtube_channel_emails or get_video_transcripts, nor any prerequisite like an Apify account/token. Usage is implied only.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve the contact email behind YouTube channels, alongside their videos and Shorts with views, likes, tags and exact publish dates. One free contact row is returned per channel. Billed to your Apify account at about $1.50 per 1,000 videos.
| Name | Required | Description | Default |
|---|---|---|---|
| channels | No | Channel handles or URLs, e.g. ["@handle", "https://youtube.com/@handle"] | |
| maxResults | No | Maximum video rows in total (default 20) | |
| newerThanDays | No | Only include videos newer than N days | |
| searchQueries | No | Keyword searches instead of explicit channels | |
| includeChannelContacts | No | Add one free contact row per channel with its About data and emails (default true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It does disclose cost ('about $1.50 per 1,000 videos') and the free contact row per channel, which is genuine operational context, but it omits authentication needs, rate limits, or failure behavior for unreachable channels.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three compact sentences with the core purpose front-loaded and the billing note last. Minor redundancy in the return-field enumeration, but no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should clarify what a result row looks like; it partially does by naming returned fields and the contact row. However, for a tool whose name promises emails, it never clarifies how emails are surfaced or what happens when a channel has none.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all five parameters are already documented in the schema, giving a baseline of 3. The description adds no parameter-level detail (e.g., the channel vs searchQueries mutual usage) beyond what the schema states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Resolve the contact email behind YouTube channels') and enumerates what is returned (videos, Shorts, views, likes, tags, publish dates). This clearly separates it from find_tiktok_creators and get_video_transcripts, though it never names those siblings explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to choose this tool over find_tiktok_creators or get_video_transcripts, nor any preconditions or exclusions. Usage is only implied by the resource name and the list of returned fields.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get transcripts for TikTok videos, Instagram Reels, YouTube videos and Shorts, and X videos. Uses the platform's own subtitles when they exist and speech-to-text when they do not. Billed to your Apify account at about $2 per 1,000 subtitle transcripts ($5 per 1,000 speech-to-text ones).
| Name | Required | Description | Default |
|---|---|---|---|
| urls | No | Video URLs across TikTok, Instagram, YouTube or X | |
| language | No | Preferred subtitle language, e.g. "en" | |
| profiles | No | Creator profile URLs to transcribe the latest videos from | |
| includeSegments | No | Include timestamped segments instead of one text block (default true) | |
| maxVideosPerProfile | No | How many of the newest videos to transcribe per profile (default 3) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does well: it discloses the transcription mechanism (platform subtitles when available, speech-to-text as fallback) and the cost model ($2/1,000 subtitle, $5/1,000 speech-to-text). It omits runtime, rate limits, or failure behavior, but cost and method are the traits an agent most needs here.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each load-bearing: coverage/scope first, mechanism second, billing third. No filler and nothing buried.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter, no-annotation tool with no output schema, the description covers scope, mechanism, and cost adequately, and the schema fills in parameter detail. It does not address return shape or the practical distinction between passing urls versus profiles, which is a minor remaining gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter is already documented in the schema; the baseline is 3. The description adds only a general statement of platform coverage and subtitle-vs-STT behavior, with no extra semantics for language, profiles, includeSegments, or maxVideosPerProfile.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Get) and resource (transcripts) and enumerates the exact platform coverage (TikTok, Instagram Reels, YouTube videos/Shorts, X). No sibling tool (find_tiktok_creators, find_youtube_channel_emails) overlaps with this resource, so the agent can route cleanly 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the resource name and the schema's urls/profiles inputs, but there is no explicit when-to-use statement, no exclusions, and no mention of alternatives. An agent can infer intent but gets no routing help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_tiktok_creatorsfind_youtube_channel_emailsget_video_transcriptsFind YouTube, TikTok and Instagram creators, get their emails and run outreach from your AI agent.
TikTok data for AI agents: videos, creators, sounds, hashtags, trends. Content + creator research.
Transcribe, read and download public Reels, TikToks and YouTube videos, plus sourced creator data
Creator discovery & analytics across YouTube, Instagram, TikTok (30M+) + brand/sponsor intel.
Add one secure layer between your agents and this server.
