Skip to main content
Glama

ProductClank

by com.productclank
OverviewDiscussionsAdmin

Launch a full TikTok campaign

launch_tiktok_campaign

One call for a full TikTok push on ONE video: community likes + up to 10 community replies (AI-drafted comments) + a 24h 'Watch & answer' quiz (viewers watch to the end and answer a counting question). Use it when the user asks for a 'full', 'full blown', 'complete' or 'combo' TikTok campaign, or for likes + replies + quiz together, instead of calling boost_post and create_watch_quiz one by one. Every size is adjustable: likes_count (1–300, default 30), replies (0–10, default 10), quiz_answers (how many people may answer, 0–1000, default 10). When the user asks for more likes or a bigger quiz, set those — do not cap them at the defaults. Price: likes 10 credits each (30 = 300, 100 = 1,000), replies 20 credits each (10 = 200), billed up front; the quiz bills 100 credits per CORRECT answer over 24h, up to quiz_answers (10 = up to 1,000, 50 = up to 5,000). FLOW: (1) call WITHOUT confirmed to get the free plan and show the user the steps and credit totals; (2) after the user says yes, call again with confirmed: true. If quiz_questions are missing on the confirmed call, the tool suggests questions from the video (40 credits) and creates nothing yet: show the user each question with its evidence, let them fix the answers, then call a third time with quiz_questions and confirmed: true. Each campaign bills separately; on a partial failure the result lists what was created — never call again blindly, it would create duplicates.

Input Schema

NameRequiredDescriptionDefault
likesNoInclude the likes boost. Default true. Size it with likes_count.
repliesNoCommunity replies (AI-drafted comments), 0–10. 20 credits each. Default 10. 0 = no replies boost.
confirmedNoSet true only after the user approved the plan and its credit totals. Omit to get the free plan.
post_textNoOptional — the video caption, if known. Skips the wait on a TikTok posted under a minute ago.
video_urlYesThe TikTok video URL (tiktok.com or vm.tiktok.com short link).
product_idNoOptional product UUID (from search_products) to tailor the replies and name the quiz.
likes_countNoHow many likes, 1–300. 10 credits each. Default 30 (300 credits).
quiz_answersNoWatch quiz size: how many people may answer, 0–1000. Billed 100 credits per CORRECT answer only. Default 10. 0 = no quiz.
quiz_questionsNoCounting questions with whole-number answers, confirmed by the user. Omit and the confirmed call suggests them first (40 credits).
reply_guidelinesNoOptional tone and content guidance for the replies.
quiz_duration_secNoVideo length in seconds, or "m:ss". Omit to read it from the TikTok / YouTube page; other platforms need it.
spread_over_hoursNoOptional — pace each boost over this many hours instead of all at once. Same price.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / likes / description
      Previous value: -"Include the likes boost (30 likes, 300 credits). Default true."New value: +"Include the likes boost. Default true. Size it with likes_count."
    • addedInput schema / properties / likes_count
      Added value: +{
+  "description": "How many likes, 1–300. 10 credits each. Default 30 (300 credits).",
+  "maximum": 300,
+  "minimum": 1,
+  "type": "integer"
+}
    • changedInput schema / properties / quiz_answers / description
      Previous value: -"Watch quiz cap: how many people may answer. Billed 100 credits per CORRECT answer only. Default 10. 0 = no quiz."New value: +"Watch quiz size: how many people may answer, 0–1000. Billed 100 credits per CORRECT answer only. Default 10. 0 = no quiz."
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare the mutation/open-world safety profile; the description adds substantial context beyond them: up-front billing, per-correct-answer quiz charging, the free-plan-then-confirmed two-step flow, the quiz-question suggestion fallback, and a partial-failure/duplicate warning. This is exactly the behavioral disclosure annotations cannot carry.

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?

Long but front-loaded: purpose, then when-to-use, then sizing/pricing, then a numbered FLOW. Every sentence carries operational weight (pricing math, flow steps, failure handling) and nothing is redundant with the schema.

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?

For a complex 12-parameter mutating tool with no output schema, the description covers purpose, alternatives, sizing, pricing, the confirmed-call flow, and failure recovery. An agent has everything needed to call it correctly across the multi-step sequence.

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 schema already documents ranges, defaults, and credits; baseline would be 3. The description adds actionable meaning beyond the schema, notably the instruction not to cap likes_count/quiz_answers at defaults when the user asks for more, plus pricing tie-ins.

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 with precise scope: 'One call for a full TikTok push on ONE video' bundling likes + replies + quiz. It explicitly distinguishes itself from boost_post and create_watch_quiz, so an agent can tell exactly what this tool does versus its siblings.

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 trigger language ('full', 'full blown', 'complete', 'combo', or likes + replies + quiz together) and names the alternative path it replaces ('instead of calling boost_post and create_watch_quiz one by one'). When-to-use is unambiguous and the substitution condition is stated.

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

All ProductClank toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources