Skip to main content
Glama

BanProof AI

by io.banproof
OverviewDiscussionsAdmin

audit_script

Audit a TikTok Shop or Amazon affiliate video script for policy violations. Detects: medical claims, guarantees, false certifications, unproven efficacy, urgency/scarcity language, fake social proof, income claims, and missing FTC disclosures (#ad/#sponsored). Returns flagged phrases, reasons, safe rewrites, and an overall risk level.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scriptYesThe full video script text to audit.
product_urlNoOptional: URL of the product page being promoted. When provided, the script is cross-checked against the actual product claims — overclaims are flagged as additional violations.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / product_url
      Added value: +{
+  "description": "Optional: URL of the product page being promoted. When provided, the script is cross-checked against the actual product claims — overclaims are flagged as additional violations.",
+  "format": "uri",
+  "type": "string"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden. It does well by disclosing the detection taxonomy and the return payload (flagged phrases, reasons, safe rewrites, overall risk level), which is meaningful behavioral context. It stops short of stating that the operation is read-only with no side effects or any auth/rate constraints.

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?

Two sentences, front-loaded with the core action before the detection list and the return summary. The categorical list is long but each item is load-bearing since it defines scope; only minor trimming would help.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

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 must describe returns — and it does, naming the flagged phrases, reasons, rewrites, and risk level. Coverage is solid for a single-purpose analysis tool; what's missing is only peripheral (read-only nature, relationship to generate_appeal).

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 both 'script' and 'product_url' are already fully documented in the schema, including the cross-check behavior of product_url. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 (audit), a specific resource (TikTok Shop or Amazon affiliate video script), and enumerates the exact violation categories detected. An agent can distinguish this immediately from the sibling generate_appeal, which is a downstream remediation tool.

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

Usage Guidelines3/5

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

Usage is implied by the purpose — you call it when you have an affiliate script to check — but there is no explicit when/when-not guidance, no prerequisites, and no mention of how it relates to generate_appeal (e.g., audit first, then appeal). Nothing is misleading, but nothing routes the agent either.

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

All BanProof AI 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