Run Script

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

Discloses that the script runs asynchronously and output goes to system log, adding value beyond annotations which only indicate destructive hint.

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 essential information. No redundant words, front-loaded with action.

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?

Describes the async behavior, output location, and how to retrieve results (get_log). No output schema, but this is sufficient for a simple execution 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 already covers all parameters with descriptions (100% coverage). Description does not add extra parameter details beyond what is in schema.

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?

Clearly states it executes a named RouterOS script. The verb 'execute' and resource 'named RouterOS script' are specific. Distinguishes from sibling tools like run_command and manage_script.

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 says it's fire-and-forget and asynchronous, and directs the agent to use get_log to see results. No explicit exclusions or alternatives, but context is clear enough.

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