run_command

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

Without annotations, the description carries the burden of disclosing behavioral traits. It correctly implies that commands are arbitrary and can be destructive (e.g., 'rm'), but does not warn about potential side effects or permissions. The mention of 'inside the sktime container' provides some isolation context.

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?

Two concise sentences with no wasted words. The purpose is front-loaded, and the example immediately clarifies the intended use.

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?

For a simple tool with one parameter and no output schema, the description adequately covers purpose and typical usage. It could mention that output is printed to stdout/stderr, but this is not critical for a run-command 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 coverage is 100% for the only parameter 'command', so the description adds limited value beyond the schema. The example 'pip install mlflow' provides a concrete usage hint, but the schema already defines the parameter as a bash command string.

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 that the tool runs arbitrary CLI/bash commands inside the sktime container, which distinguishes it from sibling tools like call_method that execute Python methods. The verb 'run' and the resource 'CLI/bash command' are specific and unambiguous.

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 provides explicit use cases: 'install missing python packages' and 'inspect the file system', with a concrete example ('pip install mlflow'). It does not explicitly state when not to use it, but the context implies it is meant for setup and debugging tasks.

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