exec_python_persistent

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

With no annotations provided, the description carries full burden. It details the persistent state mechanism (FPythonCommandEx, Public scope), output-capture caveat (stdout not captured, use unreal.log + get_log_lines), and pairing with reset_python_state. This is thorough behavioral disclosure.

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 a single paragraph that covers key points, but includes minor extraneous context (e.g., 'Tier 2 PR #45') and could be slightly more streamlined. However, it is front-loaded with the most critical information (state persistence).

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?

The tool has no output schema, so the description should explain return values. It does not explicitly state what the tool returns, but it covers the output-capture caveat, pairing, and persistent globals. Given the simplicity (single code parameter), it is mostly complete.

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?

The input schema has 100% description coverage, so the schema already defines the parameter. The description adds minimal extra context ('persistent globals dict'), but does not enhance parameter understanding beyond stating the execution environment.

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 specifies the tool's purpose: executing Python code with state persistence across calls. It explicitly contrasts with sibling execute_unreal_python, which does not persist state, making the distinction unambiguous.

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?

The description mentions pairing with reset_python_state to reset state, implying when to use that alternative. However, it does not provide explicit when-not-to-use guidelines or potential side effects of persistent state, such as unintended variable collisions.

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