Audit TikTok Shop & Amazon affiliate scripts for policy violations via MCP.
Scored across 2 tools
The two tools have clearly distinct purposes: one audits existing scripts for policy violations, while the other generates appeals for received violation notices. There is no meaningful overlap or risk of an agent selecting the wrong tool.
Both tool names follow the same verb_noun snake_case pattern: audit_script and generate_appeal. The naming is predictable and consistent.
Two tools feels thin for a general policy-compliance server, though each tool covers a distinct, useful workflow. The count is borderline but not unreasonable for a narrowly scoped niche.
The pair covers the main lifecycle well: prevent violations via audit_script and respond to violations via generate_appeal. Minor gaps exist—such as policy lookup or rewrite-only functionality—but audit_script already includes safe rewrites, so the core workflow is not blocked.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| script | Yes | The full video script text to audit. | |
| product_url | No | 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. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds genuinely useful behavioral context by listing exactly what the audit detects and what it returns (flagged phrases, reasons, safe rewrites, risk level), going beyond the annotations.
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?
The description is compact and front-loaded: it states the action first, then enumerates detection categories and return values in a structured way. Every sentence earns its place, with no filler or repetition of schema fields.
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?
Even though there is no output schema, the description names all return components and detection categories. The schema covers both parameters, and the annotations cover safety and idempotence, so an agent has enough information to call the tool correctly without additional documentation.
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%, and the schema already documents both script and product_url in detail, including the cross-checking behavior for product_url. The description adds no additional parameter-level information, so the baseline of 3 is appropriate.
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?
The description uses a specific verb ('Audit'), a clear resource ('TikTok Shop or Amazon affiliate video script'), and enumerates concrete detection categories. It is clearly distinct from the sibling generate_appeal, since auditing for violations is a different operation from generating an appeal.
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 clearly implies when to use the tool: when a script needs a policy-compliance check. However, it never mentions the sibling generate_appeal or provides when/when-not guidance, so an agent must infer the selection decision rather than being explicitly routed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a ready-to-submit appeal response for a TikTok, Amazon, or YouTube policy violation notice. Stays within TikTok's 800-character appeal limit. Paste the violation notice text you received and specify the platform.
| Name | Required | Description | Default |
|---|---|---|---|
| platform | Yes | The platform that issued the violation: tiktok, amazon, or youtube. | |
| violation_notice | Yes | The full text of the violation notice or strike you received from the platform. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds useful behavioral context beyond annotations by noting that output is 'ready-to-submit' and that it 'stays within TikTok's 800-character appeal limit.' However, the annotations are all false/negative and provide little guidance, and the description does not disclose output structure, platform-specific formatting, or the need for user review before submission.
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?
The description is appropriately sized at three short sentences. The primary purpose is front-loaded, followed by a key output constraint and then direct usage guidance. Every sentence earns its place with 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?
For a two-parameter generation tool with no output schema, the description covers the essential context: what it generates, for which platforms, the character-limit constraint, and how to invoke it. It could be more complete by explicitly describing the output format or noting that generated appeals may require review, but the core information needed to call it correctly is present.
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 baseline is 3 even without additional parameter explanations in the description. The description's 'paste the violation notice text' and 'specify the platform' only echo the schema and add no new semantic detail about either parameter.
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?
The description clearly states a specific verb and resource: 'Generate a ready-to-submit appeal response' for policy violation notices on TikTok, Amazon, or YouTube. It is immediately distinguishable from the sibling tool audit_script, which covers a different domain entirely.
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 clear usage context: use this tool when the user has received a platform policy violation notice and needs an appeal response. It instructs the user to paste the notice and specify the platform, but it does not explicitly state when not to use it or mention alternatives.
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.
audit_script1 field changedInput schema / properties / product_urlAdded 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"
+}generate_appealaudit_script
Add one secure layer between your agents and this server.