record_decision_outcome
Record what ACTUALLY happened after a decided decision — once, separately from the decision text, because decision quality and outcome quality are different things and the confidence stated at decision time is scored against this. The verdict (held | partly | did_not_hold) is what calibration sco...
This record as markdown: /tools/adrata-adrata-mcp/record-decision-outcome.md
What record_decision_outcome does on Adrata
AI agents use record_decision_outcome to create or update resources in Adrata, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adrata environment.
Why record_decision_outcome is rated Medium
An AI agent can call record_decision_outcome faster than any human can review: one bad instruction and it creates or modifies resources in Adrata by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs record_decision_outcome safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For record_decision_outcome, this is the rule to start with:
record_decision_outcome stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every record_decision_outcome call is checked against it from then on.
Questions about record_decision_outcome
Record what ACTUALLY happened after a decided decision — once, separately from the decision text, because decision quality and outcome quality are different things and the confidence stated at decision time is scored against this. The verdict (held | partly | did_not_hold) is what calibration scores: without it the outcome is prose the Brier score cannot read, so it is required here. Only after status is decided; the API refuses a second outcome. Write what was observed, not a re-argument of the call.${GOVERNED_NOTE}. It is categorised as a Write tool in the Adrata MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Adrata MCP server in PolicyLayer and add a rule for record_decision_outcome: 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 Adrata. Nothing to install.
record_decision_outcome 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 record_decision_outcome 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 record_decision_outcome. 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.
record_decision_outcome is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
This server
Across the catalogue