execute_script

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

With no annotations, the description carries the full behavioral burden and does so thoroughly. It discloses the disposable worker nature, the isolation boundary (reliability vs. hostile-code), the ability to read/write files, start processes, make destructive changes with user authority, timeout behavior (default, acceptance of finite values, null disables, cancellation termination), and points to get_docs. This is comprehensive and transparent.

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 slightly long but every sentence adds value: purpose, safety caveat, timeout semantics, and a helpful pointer to get_docs. It's front-loaded with the core action and efficiently organized, though it could be tightened by removing minor redundancy (e.g., 'any positive finite timeout is accepted' is somewhat implied by 'default timeout is 300 seconds').

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 complexity of code execution, the description covers the essential aspects: environment (local_user, disposable), capabilities and risks, timeout handling, and discovery of commands via get_docs. The presence of an output schema relives it from explaining return values. No critical information is missing for an agent to correctly invoke and handle the tool.

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 0%, so the description must compensate. It does: 'port' is clarified as the Archicad port, 'script' is the Python code to execute, and 'timeout_seconds' is fully explained (default 300, positive finite accepted, null disables, and cancellation behavior). All three parameters gain meaning far beyond the bare schema types.

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 the tool's purpose: 'Execute Python in a disposable same-account local_user worker against the selected Archicad port.' It identifies a specific verb (execute), resource (Python script), and target (Archicad port), distinguishing it from the sibling list/get tools that are informational.

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 implies use cases (running Python scripts) and provides a pointer to get_docs for command discovery. However, it doesn't explicitly state when NOT to use this tool or name direct alternatives, though siblings are clearly non-execution tools. The safety warning also suggests caution, but not an explicit exclusion.

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