Run Lua code in the live Dragon's Dogma 2 game to inspect or change state; captures print() output and returned values, with phase='update' for UpdateBehavior changes.
Run a Lua chunk in the running game; print() output and returned values come back. phase='update' runs it inside the game's UpdateBehavior (required for state changes).
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| phase | No | frame | |
| timeout | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that print() output and returned values come back, and that state changes require phase='update', but it does not mention risks of arbitrary code execution, timeout behavior, error handling, or whether the call can destabilize the game.
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 tight sentences with no waste. The primary action is front-loaded, and the critical phase='update' condition follows immediately.
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?
An output schema exists, so return-value explanation is not required, and the description covers the core purpose and update-phase requirement. However, for an arbitrary-code-execution tool with no annotations and 0% schema descriptions, the missing timeout semantics, default frame phase, and safety context leave meaningful gaps.
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 0%, so the description must compensate. It explains 'code' as a Lua chunk and partially explains 'phase' by noting phase='update' for state changes, but it never explains the default phase='frame', nor does it describe the 'timeout' parameter or its units/behavior.
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 uses a specific verb and resource: 'Run a Lua chunk in the running game.' It clearly distinguishes the tool as a general Lua execution mechanism, though it does not explicitly contrast itself with the many dd2_* sibling tools that expose specific game functionality.
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 provides a concrete usage rule: phase='update' runs inside UpdateBehavior and is 'required for state changes.' This tells the agent when to choose the update phase, but it does not say when to use dd2_eval at all versus the domain-specific sibling tools such as dd2_give_item or dd2_job.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.