vw_exec_python

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

Adds substantial behavior beyond annotations: return contents (stdout, last expression or `result`, traceback), embedded Python version 3.9, the handle-lifetime constraint with the vs.GetObjectUuid workaround, and the non-obvious failure mode of a modal 'Script Errors' dialog rather than an exception. Nothing in the structured fields conveys any of this.

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?

Front-loaded with the essential purpose in the first clause, then each subsequent sentence delivers a distinct operational fact (returns, runtime version, handle lifetime, dialog gotcha, flag semantics). No filler.

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?

With no output schema present, the description explicitly documents what is returned, and it covers the environment, safety knob, and failure modes an agent needs to invoke this high-variance tool correctly.

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 carry the load. It defines the execution context for `code` (`vs` in scope, returns last expression or `result`) and fully explains the operational meaning of `modifies_document` including its effect on vw_revert_last. Minor gaps: no mention of code size/time limits or argument passing, but the critical semantics are covered.

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 resource ('Run arbitrary Python inside Vectorworks') plus the execution environment ('with `vs` in scope'). It is immediately distinguishable from siblings like vw_vs_lookup (signature checking) and the read-only list/get tools.

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?

Explicitly routes to vw_vs_lookup before calling ('A wrong vs.* signature can pop a modal... check with vw_vs_lookup first'), and tells the agent when to set modifies_document=False versus when not to, citing the vw_revert_last interaction as the consequence.

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