tiktok_ads_diagnosis
TikTok’s issues-and-suggestions diagnosis for the ad groups on an ad account — its own read on why delivery is underperforming, in three categories: CREATIVE (no background music, video too short, resolution too low), BID_AND_BUDGET (a suggested bid or budget, a recommendation to switch to Maximu...
This record as markdown: /tools/hermoso/tiktok-ads-diagnosis.md
What tiktok_ads_diagnosis does on Hermoso
AI agents call tiktok_ads_diagnosis to retrieve information from Hermoso without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why tiktok_ads_diagnosis is rated Low
Even though tiktok_ads_diagnosis only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs tiktok_ads_diagnosis safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hermoso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tiktok_ads_diagnosis, this is the rule to start with:
tiktok_ads_diagnosis is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hermoso, apply this rule, and every tiktok_ads_diagnosis call is checked against it from then on.
Questions about tiktok_ads_diagnosis
TikTok’s issues-and-suggestions diagnosis for the ad groups on an ad account — its own read on why delivery is underperforming, in three categories: CREATIVE (no background music, video too short, resolution too low), BID_AND_BUDGET (a suggested bid or budget, a recommendation to switch to Maximum Delivery, and the full Estimated Delivery Results tables pairing nine bid levels or fifteen budget levels with their estimated cost, conversions, CPA and impressions), and EVENT_TRACK (a pixel that has recorded nothing for seven days, which means the ad group is optimising toward an event nothing is firing). Every issue code comes back with a plain sentence saying what to DO about it. Warning: AN EMPTY ANSWER IS NOT A CLEAN BILL OF HEALTH: TikTok diagnoses ACTIVE ad groups only and omits any ad group it has no suggestions for, so a missing ad group is EITHER healthy OR not currently active and TikTok does not distinguish the two. At most 20 ad groups per call. Read-only, free. It is categorised as a Read tool in the Hermoso MCP Server, which means it retrieves data without modifying state.
Register the Hermoso MCP server in PolicyLayer and add a rule for tiktok_ads_diagnosis: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hermoso. Nothing to install.
tiktok_ads_diagnosis is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tiktok_ads_diagnosis rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for tiktok_ads_diagnosis. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
tiktok_ads_diagnosis is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hermoso, and thousands of servers like it.
This server
Across the catalogue