UNLEARN a calibration case whose label turned out wrong or obsolete — retires it (active=false) so the recalibration gate stops scoring it. To correct, retire the wrong case then record_outcome the right one. Operator-only.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| case_id | Yes | ||
| operator_key | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the behavioral effect (active=false, stops scoring) and the intended workflow. With no annotations, this is good but could mention reversibility or side effects.
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 with no wasted words. The key action ('UNLEARN') is frontloaded. Could benefit from bullet points for parameters.
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?
Adequate for a simple retirement action but lacks parameter descriptions and output details. The calibration domain context is assumed.
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?
Description does not explain the three parameters beyond their names. With 0% schema coverage, the agent gets no help on what values to provide for reason, case_id, or operator_key.
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?
Clearly states the tool retires a calibration case by setting active=false when labels are wrong or obsolete. Distinguishes from sibling record_outcome by describing a two-step workflow.
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?
Explicitly states when to use (wrong/obsolete label), how to use (retire then record_outcome), and restrictions (Operator-only).
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.