suggest_tests

What suggest_tests does on Trace

AI agents call suggest_tests to retrieve information from Trace without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why suggest_tests is rated Low

The tool performs analysis and suggestion of test cases based on existing code symbols. This is a read-only operation: it retrieves information about a symbol and generates recommendations without side effects such as creating, modifying, deleting, or executing code. Even though it involves AI-driven analysis, the output is purely advisory (suggestions), not an action that changes state or runs operations.

From the tool's definition Tool description states 'Suggest test cases for a symbol using AI' — a suggestive/analytical operation that reads code symbols and proposes test cases without modifying, deleting, or executing code.

The rule that runs suggest_tests safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For suggest_tests, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "suggest_tests": {}
  }
}

Questions about suggest_tests