Debugger: Evaluate (REPL)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly states that execution can have side effects and is not read-only, reinforcing the annotations (readOnlyHint=false, destructiveHint=true). It also adds useful behavioral context not present in the annotations: output streams to the device console, and compile/runtime errors are reported.

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?

The description is compact and front-loaded, opening with the action, then giving examples, followed by the side-effect warning and alternative routing. Every sentence adds necessary information without filler.

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?

For a tool with no output schema, the description adequately covers the critical context: halted-frame requirement, side-effect warning, output destination, and error reporting. It leaves default behavior to the schema, which already documents threadIndex and stackFrameIndex defaults, so the overall context is sufficient.

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?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds useful examples for the expression parameter and notes that stackFrameIndex/threadIndex select the scope, but this largely restates what the schema already provides.

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?

The description clearly identifies the operation as running a BrightScript expression/statement in the halted frame (the debug-console REPL), with concrete examples such as print m.top.count. This distinguishes it from read-only variable inspection tools like debugger_get_variables.

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?

It states the core precondition that the target must be HALTED and explicitly routes plain variable reads to debugger_get_variables. It also warns that evaluation can have side effects, helping the agent decide when to use it versus safer alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.