live_run_python

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

With no annotations provided, the description carries the full behavioral disclosure burden. It usefully explains that GIMP modules and helpers are in scope and that a `result` variable must be assigned to return a value. However, it does not disclose that arbitrary Python execution can mutate or destroy GIMP state, crash the session, or have irreversible side effects, which is a significant transparency gap for an unbounded execution tool.

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 short, front-loaded with the main purpose, and every sentence earns its place: execution semantics, scope context, return-value convention, use-case, and prerequisite. No filler or redundant restating of the tool name.

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?

Given the presence of an output schema, the description does not need to explain return structure. It covers the parameter, the execution environment, the return mechanism, and the prerequisite. The main missing piece is a warning about the destructive or uncontrolled nature of raw Python execution, which matters for a tool of this complexity and power.

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 coverage is 0%, so the description must compensate. It does meaningfully: it tells the agent that `code` is Python to execute inside GIMP, that modules are already in scope, and that assigning to `result` controls the return value. This gives the single parameter real semantic grounding beyond the bare name 'code'.

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 states a specific verb+resource: 'Execute Python inside the running GIMP and return `result`'. It also differentiates itself from the typed sibling tools by describing itself as an 'escape hatch for anything the typed tools above do not cover', so an agent can distinguish it at a glance.

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 explicitly tells the agent when to use this tool: when the typed tools do not cover the needed operation. It also establishes the prerequisite that the bridge plug-in must be present. This provides clear when-to-use context and points to the sibling tools as the preferred alternative.

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