execute_python_script

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

The description discloses that the tool runs 'arbitrary, un-sandboxed code' and specifies the return format as '{result, stdout, stderr}'. Annotations already indicate destructiveHint=true and readOnlyHint=false, and the description adds valuable context beyond these annotations without contradiction.

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 three sentences long, no filler. The first sentence states the purpose, the second adds technical context, and the third provides usage guidance. Well-structured and front-loaded.

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 tool's complexity and destructive nature, the description covers purpose, return format, scope of available APIs, and usage recommendations. It is sufficiently complete, though a brief mention of potential side effects or safety considerations would be beneficial.

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%, but the description adds extra semantic value by explaining that a single expression returns its value and multi-line scripts can set 'result'. This goes beyond the schema's parameter descriptions.

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 'Execute a Python script in TouchDesigner's interpreter and capture output', using a specific verb and resource. It distinguishes itself from sibling tools by advising to use dedicated node tools for routine edits and reserving this tool for logic not covered elsewhere.

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 explicitly provides when-to-use ('logic the other tools do not cover') and when-not-to ('prefer dedicated node tools for routine edits'), along with a caution that it runs arbitrary, un-sandboxed code.

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