audit_scriptAudit a TikTok Shop or Amazon affiliate video script for policy violations (medical claims, guarantees, false certifications, unproven efficacy). Returns flagged phrases, reasons, safe rewrites, and an overall risk level.
| Name | Required | Description | Default |
|---|---|---|---|
| script | Yes | The full video script text to audit. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds value by disclosing the analysis dimensions (medical claims, guarantees, false certifications, unproven efficacy) and the return payload (flagged phrases, reasons, safe rewrites, risk level). No contradiction.
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?
Two sentences front-load the core action and scoping, then list outputs. There is no filler or repetition of schema content.
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 single-parameter, read-only tool with no output schema, the description supplies all needed context: target platform, violation categories, return values, and risk level. Annotations cover mutability/idempotence and the schema covers the parameter.
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?
The schema covers 100% of parameters: the required 'script' field is described as 'The full video script text to audit.' The description adds context about the script type but not additional parameter semantics, so the baseline 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'), identifies the exact resource ('TikTok Shop or Amazon affiliate video script'), names policy categories, and states the outputs. With no sibling tools, differentiation is not required.
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?
It clearly scopes the tool to affiliate video scripts for TikTok Shop/Amazon policy review. It does not offer explicit when-not-to-use guidance, but with no siblings and a clear professional context, the intended use is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
There is only one tool, so there is no possibility of an agent confusing it with another tool. Its purpose is clearly and narrowly defined.
The single tool name follows a clear verb_noun convention. With only one name, there are no conflicting naming styles or patterns to confuse an agent.
One tool is borderline: it covers the core audit action, but the server feels very thin. Additional related operations such as batch audits or historical audit retrieval would make the server feel more complete.
The audit tool fully covers its stated core workflow: flagging violations, explaining them, suggesting rewrites, and giving a risk level. Minor gaps exist around policy configuration and audit history, but they are not required for the primary use case.