check_gpu

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

Given no annotations, the description discloses that it performs an actual check, returns status with remediation steps, and emphasizes factual accuracy over UI text.

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 succinct sentences that convey necessary information without redundancy.

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?

Adequately covers prerequisites, return status indication, and behavior for a no-parameter tool, though success return format is not detailed.

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 in the schema; description adds meaningful context about the tool's behavior beyond the 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 checks GPU availability using nvidia-smi, distinguishing it from related tools like check_runtime or read_gpu_monitor.

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 lists prerequisites (open_colab_browser_connection and connect_runtime) and warns against relying on UI text alone, providing clear context for when to use the tool.

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