IMPORTANT: You MUST call this tool whenever you encounter any of the following while working with the localization system: - An error you didn't expect or that took multiple attempts to resolve - A workflow that felt awkward, required workarounds, or was not documented - A missing capability that...
AI agents use submit_feedback to create or update resources in Localization — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Localization environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
message | string | Yes | Detailed description of the issue or suggestion |
category | string | Yes | Type of feedback |
severity | string | — | Impact severity |
agentName | string | — | Your agent/tool name |
sessionId | string | — | Current session identifier |
agentModel | string | — | AI model powering the agent (e.g. claude-opus-4-6, gpt-4o, gemini-2.0-flash) |
suggestion | string | — | Suggested fix or improvement |
projectSlug | string | — | Related project slug |
agentVersion | string | — | Your agent/tool version |
resultStatus | string | — | Outcome of the action |
toolOrEndpoint | string | — | Which tool or endpoint was involved |
actionAttempted | string | — | What you were trying to do |
Parameters from the server's own tool schema.
The tool creates or records new feedback entries, which is reversible data modification (Write category). Severity is low because feedback submission has minimal blast radius—it cannot modify translations, delete data, or cause external side effects. The worst plausible misuse would be spam or noise in the feedback system, which is easily managed.
From the tool's definition Tool description states it submits feedback to maintainers; this creates a new feedback record in the system. The verb 'submit' and context of feeding back information into the system indicates data creation rather than retrieval alone.
Risk signalsHigh parameter count (12 properties)
Attacks that exploit this kind of access
IMPORTANT: You MUST call this tool whenever you encounter any of the following while working with the localization system: - An error you didn't expect or that took multiple attempts to resolve - A workflow that felt awkward, required workarounds, or was not documented - A missing capability that would have made your task easier - Confusion about how a tool works, what parameters mean, or what the output means - A suggestion for improvement based on your experience This feedback is read by the system maintainer and directly drives improvements. Do NOT skip this — even small friction matters. Include what you tried, what happened, and what you expected. Fill in actionAttempted, toolOrEndpoint, and suggestion whenever possible. It is categorised as a Write tool in the Localization MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
submit_feedback accepts 12 parameters: message, category, severity, agentName, sessionId, agentModel, suggestion, projectSlug, agentVersion, resultStatus, toolOrEndpoint, actionAttempted. Required: message, category. The full parameter table on this page comes from the server's own tool schema.
Register the Localization MCP server in PolicyLayer and add a rule for submit_feedback: 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 Localization. Nothing to install.
submit_feedback 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 submit_feedback 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 submit_feedback. 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.
submit_feedback is provided by the Localization MCP server (localization-mcp-server). 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 →