Run Script

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

With no annotations, the description carries full burden, and it does disclose genuinely useful behavior: the exact command line, -noui/-nowarnings flags, that cwd is the script's parent directory, and that Exit(n) yields custom codes. However, it never states return format, safety/destructiveness, or failure semantics for executing arbitrary script 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?

Front-loaded with the core action, followed by compact usage detail. Every line is relevant; only the command-line line borders on redundant with the schema but adds exit_mode semantics.

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 needn't be explained. For a 5-param execution tool, the description covers the key runtime context (cwd, CLI invocation, exit handling) that the bare schema cannot convey, leaving only script_args/timeout_sec light.

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 maps the data file and script file and hints at exit_mode via the -<exit_mode> flag, but says nothing about script_args or timeout_sec (both non-obvious with defaults like 120s).

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+resource (run a 010 Editor .1sc script, optionally on a data file) and distinguishes itself implicitly from run_template by noting scripts can call RunTemplate. Clear, though the sibling distinction is only implied.

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?

No explicit guidance on when to use run_script vs run_template, or on prerequisites/permissions for executing arbitrary scripts. The RunTemplate mention hints at the relationship but is a runtime detail, not routing guidance.

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