get_runtime_errors

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

Discloses stateful 'since the last call' behavior and return content (structured entries with error type, source, stack traces). Adds prerequisite of run_interactive. Annotations already cover read-only/destructive hints, and description does not contradict them.

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 sentences, front-loaded with the core purpose, concise and free of filler. Every sentence adds value.

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?

With one optional parameter and no output schema, the description covers the return structure and prerequisites well. It doesn't explicitly describe the consuming behavior of the default clear=true, but the schema's parameter description fills that gap.

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?

The only parameter, 'clear', has full schema description coverage (100%). The description adds no additional parameter detail, but the schema already clearly explains the default behavior and peek option, so baseline 3 is appropriate.

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?

Description uses a specific verb ('Retrieve') and clearly identifies the resource: runtime errors, warnings, and backtraces since the last call. This distinguishes it from sibling get_debug_output by focusing on structured runtime errors with stack traces.

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?

States explicit prerequisites ('Requires Godot 4.5+ and run_interactive'), giving clear context for when the tool can be used. However, it does not explicitly mention alternatives or when not to use it, so it falls short of full guidance.

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