run_script

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

Annotations already mark this as destructiveHint: true. The description adds valuable context: it details the execution model (live project, full scene tree access), error handling (errors escalate vs warnings based on return), and the fact that debug output goes to a different tool. This exceeds what annotations alone provide.

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 efficiently structured: intended use, requirements, behavior, and return format. Every sentence adds necessary information without redundancy. It is front-loaded with the core purpose.

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 executing arbitrary scripts and the presence of output schema (implied by return format description), the description covers all essential aspects: prerequisites, script constraints, error modes, debug output routing, and the structure of the response. No gaps remain for an agent to select or invoke the tool correctly.

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?

Input schema covers 100% of parameters with descriptions. The description restates the constraints for 'script' and explains the default timeout for 'timeout'. This adds minimal additional value beyond the schema, resulting in a baseline score of 3.

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 'Execute a custom GDScript in the live running project with full scene tree access.' This specific verb+resource combination immediately conveys the tool's purpose. It distinguishes itself from sibling tools like 'get_debug_output' or 'add_node' by focusing on arbitrary script execution.

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 prerequisites ('Requires an active runtime session') and script requirements ('must extend RefCounted and define func execute...'). It also explains that print() appears in get_debug_output, guiding the agent on debugging. While it doesn't explicitly list when not to use, the context and siblings imply appropriate use cases.

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