execute_pythonRun Python code inside a Houdini process with hou available to automate scene tasks, inspect nodes, or modify parameters when typed tools are insufficient.
Run Python in the Houdini process with hou available. Prefer typed tools when possible.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so the safety profile is structured. The description adds real context beyond that: execution happens in-process with the hou module available, meaning scene mutations persist in the live session. It omits anything about return values, stdout capture, timeouts, or error behavior for arbitrary code.
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 short sentences, zero padding, with the environment constraint front-loaded before the routing hint. Nothing is wasted.
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 values need not be explained. However, for an arbitrary-code-execution tool marked destructive, the description is thin on execution semantics (persistence of mutations, error propagation, whether the call blocks) that an agent needs before invoking it.
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?
Only one parameter ('code') with 0% schema description coverage, so the schema supplies no meaning on its own. The description only indirectly indicates it is Python source executed against hou; it says nothing about the expected code shape, whether expressions or statements are allowed, or how results are surfaced.
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?
States a specific verb and environment: 'Run Python in the Houdini process with hou available.' That distinguishes it from the typed siblings (create_node, set_parameter) which manipulate the scene declaratively. Slightly less than a 5 because 'the Houdini process' and 'hou' assume host-specific knowledge not spelled out.
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?
'Prefer typed tools when possible' gives a directional preference toward the sibling tools, but it never states when this tool is actually necessary (e.g., batch operations, inspecting hou state, computing values) nor when it must not be used. Usage is implied rather than defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.