gpu_flush_models

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

Describes the two main effects (unloading models, emptying CUDA cache). With no annotations, this is adequate for a simple removal tool, though it could mention if it disrupts ongoing processes.

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 short sentences, no wasted words. Front-loaded with the main action and comparison.

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 zero parameters and no output schema, the description fully covers the tool's purpose and behavior. The comparison to vram_flush adds context.

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?

No parameters exist, so the description cannot add parameter meaning. Baseline 4 is appropriate as it's not required to elaborate.

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 clearly states the action (unload all models, empty CUDA cache) and resource (models from VRAM in ComfyUI). It also distinguishes from sibling tool vram_flush by stating it's more thorough.

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?

Provides a comparison with vram_flush ('more thorough'), guiding when to use. Lacks explicit when-not or alternative scenarios, but the comparison is helpful context.

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