Skip to main content
Glama

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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "script": "<script>"
    },
    "name": "audit_script"
  }
}

Input 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
    • removedInput schema / additionalProperties
      Removed value: -false
  2. 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"
      +}
  3. First observed

TDQS

A4/5.0
Behavior3/5

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

The annotations declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the agent already knows this is a non-read-only call against open-world data. The description adds the shape of the analysis result (flagged phrases, reasons, safe rewrites, risk level), but it never explains what makes the call non-read-only or non-idempotent, nor whether it costs credits or hits an external model.

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?

Two sentences: the first states purpose, the second lists detection categories and return shape. The verb and resource are front-loaded, and no sentence is filler.

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?

With only two parameters, full schema coverage, and no output schema, the description covers the key gaps by naming the return payload and the detection taxonomy. The remaining unaddressed item is the meaning of the readOnlyHint=false annotation, which an agent would want explained.

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 description coverage is 100%, so both parameters are already fully documented, establishing a baseline of 3. The description adds a small amount of value beyond that by naming the concrete payoff of the tool (flagged phrases, reasons, safe rewrites, and an overall risk level), which frames how the single required input is consumed.

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?

Specific verb (audit) plus a precisely scoped resource (TikTok Shop / Amazon affiliate video script) and an enumerated list of the eight violation classes it detects. Nothing about it could be confused with the sibling generate_appeal, which produces appeals rather than findings.

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?

The phrase 'for policy violations' implies the pre-publication review context, but the description never states when to reach for this tool, when not to, or how results should feed generate_appeal. Usage is inferable rather than prescribed.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.