skills_run_script

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

Since no annotations are provided, the description carries full burden. It discloses that script source is never returned, scripts run sandboxed with a 30-second timeout, input_data is passed as environment variables, and the two-phase workflow. It could add details on timeout behavior or error handling, but covers key aspects.

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 concise, well-structured with a clear purpose statement, bullet points for two-phase use, and succinct explanations. Every sentence adds value without redundancy.

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 no annotations and 0% schema coverage, the description covers main behavior but omits the list_only parameter. Output schema exists (so return values need not be detailed). Overall, slightly incomplete due to missing parameter explanation.

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 description must explain params. It explains filename (including the 'list' value) and input_data (env vars). However, it does not explain skill_id (though perhaps self-evident) or list_only boolean, which is a gap. Adds value but incomplete.

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 explicitly states the tool executes a helper script bundled with a skill and never returns the script source, only stdout, stderr, and exit code. It distinguishes itself from siblings (find, get_asset, etc.) by focusing on script execution and the two-phase listing vs. running functionality.

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?

It provides clear guidance: 'Only call when skill instructions direct you to run a specific script.' The two-phase usage (call with 'list' then specific filename) is explained. However, it does not explicitly state when not to use other sibling tools, though the context implies it.

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