Skip to main content
Glama

hooklayer

by io.github.khan-ashifur

viral_remix

Take a viral video and produce a fresh script that mirrors its structure and energy pattern for a new topic. Returns the extracted formula, scene-by-scene script with voiceover and visuals, camera directions, and text overlays. Use when the user finds a video they want to replicate the structure of. Pass either a video URL (TikTok, YouTube, or Instagram) or a transcript directly. When promoting a specific product, ALWAYS pass target_product + verified_product_facts so the generator does not fabricate product details.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nicheNoOptional niche hint
my_topicNoDEPRECATED alias for target_topic. Legacy clients only. Normalized internally.
platformNoTarget platform for the remix. Adjusts pacing and CTA style if provided.
source_urlNoTikTok/YouTube/Instagram URL — transcript will be auto-extracted
transcriptNoPre-extracted transcript (alternative to source_url, faster)
target_topicNoWhat the remix should be about. Default: same niche as original.
target_productNoThe product the remix should promote. When provided, the generator will NOT invent product names, prices, timelines, features, or customer stories. Combined with verified_product_facts, this forces on-topic + grounded output.
verified_product_factsNoFacts the generator is allowed to cite about target_product (e.g. "runs inside ChatGPT and Claude", "9 tools for viral research"). Every specific product claim in the generated script is checked against this list — unsupported claims populate unsupported_claims[] and downgrade quality. If target_product is passed WITHOUT verified_product_facts, the response will land at degraded quality (generation cannot be grounded).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
overlaysNoText overlay suggestions per scene
from_paygNoWhether credits came from pay-as-you-go balance
verify_hookNoThe hook plus a suggested follow-up: the caller may pass it to score_hook for a structurally-independent score (the script generator deliberately does NOT self-rate). Informational only, not an instruction to call anything.
camera_shotsNoPhone-native camera direction per scene
fresh_scriptNoComplete scene-by-scene script mirroring the source structure
cta_archetypeNoWhich CTA archetype the generator picked. Comment_gate is the failure-mode default for AI script generators; rotation tells you whether the prompt is working.
ugc_authenticityNoTripwire for ad-shaped drift. Detected via regex on the produced script, not the model self-grade. If level=ad_leaning, surface to the user before shipping.
credits_remainingNoCredits remaining after this call
extracted_formulaNoThe viral DNA formula extracted from the source
from_subscriptionNoWhether credits came from subscription
structural_skeletonNoWhich structural skeleton the generator used (confession_to_result, mistake_to_correction, etc). Surfaces rotation across the fleet.

TDQS

A4.3/5.0
Behavior4/5

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

The description discloses meaningful behavioral details beyond annotations: it returns a structured script package, and it states that passing target_product + verified_product_facts prevents the generator from fabricating product details. Annotations already cover read-only/destructive/idempotent hints, and the description does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences with no filler: purpose, output, usage trigger, and critical product-grounding rule. It is front-loaded and every sentence earns its place.

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?

Given the rich input schema, output schema, and annotations, the description covers the essential invocation decisions: what the tool does, what inputs are acceptable, and the mandatory product-facts pairing for grounded promotion. No critical information for selecting or calling the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 eight parameters thoroughly. The description adds 'ALWAYS pass target_product + verified_product_facts' and 'Pass either a video URL or a transcript directly,' but these largely restate or emphasize schema semantics rather than introducing new parameter meaning.

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 states a specific verb and resource: 'Take a viral video and produce a fresh script that mirrors its structure and energy pattern for a new topic.' It also enumerates concrete outputs (formula, scene-by-scene script, voiceover, visuals, camera directions, text overlays), making the tool's function unmistakable and distinct from siblings like find_viral_template.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit trigger condition: 'Use when the user finds a video they want to replicate the structure of.' It also provides input-mode guidance (URL vs transcript) and a product-promotion rule. It does not explicitly state when not to use it or name alternative tools, so it falls short of a 5.

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

All hooklayer toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Each tool targets a distinct purpose: analysis, trend research, scoring, creation, and tracking. The lifecycle tools (analyze_account, watch_account, get_changes) are related but clearly delineated by baseline creation vs. comparison. score_hook and predict_virality could be mildly confused since both score content, though descriptions clarify hook-level vs. full-draft scope.

Naming Consistency4/5

Nine of twelve tools follow the verb_noun pattern (analyze_account, find_viral_template, get_changes, list_watches, match_voice, predict_virality, score_hook, search_videos, watch_account). Three deviate: brief_to_blueprint, trend_pulse, and viral_remix use prepositional or noun-based naming, creating minor inconsistency but not confusion.

Tool Count5/5

Twelve tools for a short-form content intelligence platform feels well-scoped. The surface covers research (4 tools), creation (3), validation (2), and tracking (3), with each tool earning its place. This sits comfortably within the ideal 3-15 range for a domain-specific server.

Completeness3/5

The research, creation, and validation workflows are well-covered, but the tracking lifecycle has a notable gap: watch_account and list_watches exist with no unwatch/remove_watch tool, and get_changes implies persistence without a way to manage it. Also missing is a single-video deep-dive tool (analyze_account only covers videos within full account analysis) and direct creator-to-creator comparison.

Resources