Submit a friction log after completing setup to help improve the tru service. Include what worked well, what was confusing or broken, and general error descriptions. Do NOT include API keys, tokens, secrets, code snippets, or file paths — these are automatically stripped.
AI agents use dev_submit_friction_log to create or update resources in Tru — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tru environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
raw_errors | array | — | Error messages encountered during setup. |
friction_notes | string | Yes | Narrative friction log: what worked, what was confusing, what broke, suggestions. Be specific about section numbers and include error messages. |
section_ratings | object | — | Rate each phase. Keys: '1_register', '2_payments', '3_provisioning', '4_go_live'. |
skipped_sections | array | — | Section identifiers skipped during setup. |
completed_sections | array | — | Section identifiers completed during setup. |
time_spent_minutes | number | — | Estimated total setup time in minutes. |
Parameters from the server's own tool schema.
This tool creates new records (friction logs) in the tru service's feedback system. It is reversible (logs can be deleted or edited) and has no side effects on billing, provisioning, or authentication systems. The emphasis on not including sensitive data suggests the system itself handles sanitization, further indicating this is a straightforward write operation for diagnostic/feedback purposes.
From the tool's definition Tool description states it will 'Submit a friction log' which involves creating or recording data. The explicit instruction to exclude 'API keys, tokens, secrets, code snippets, or file paths' confirms this is a data submission endpoint that writes feedback…
Attacks that exploit this kind of access
Submit a friction log after completing setup to help improve the tru service. Include what worked well, what was confusing or broken, and general error descriptions. Do NOT include API keys, tokens, secrets, code snippets, or file paths — these are automatically stripped. It is categorised as a Write tool in the Tru MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
dev_submit_friction_log accepts 6 parameters: raw_errors, friction_notes, section_ratings, skipped_sections, completed_sections, time_spent_minutes. Required: friction_notes. The full parameter table on this page comes from the server's own tool schema.
Register the Tru MCP server in PolicyLayer and add a rule for dev_submit_friction_log: 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 Tru. Nothing to install.
dev_submit_friction_log is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dev_submit_friction_log 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 dev_submit_friction_log. 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.
dev_submit_friction_log is provided by the Tru MCP server (tru-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →