system_diagnostics

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

With no annotations provided, the description carries the full behavioral burden. The verb 'Returns' implies a read-only operation, which is useful, but nothing is said about side effects, cost/latency, or failure modes (e.g., what happens if CUDA is unavailable).

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?

A single, front-loaded sentence lists exactly what the tool returns with no filler. Every word earns its place, and the structure conveys the complete scope efficiently.

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?

For a simple parameterless diagnostics tool, the description names all key output categories. However, with no output schema, the agent does not know the exact response format or field names, which would be helpful but is not critical for deciding to call it.

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 tool has zero parameters, so the baseline is 4. The description correctly avoids inventing parameter explanations and the empty input schema fully covers parameter needs.

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 uses a specific verb ('Returns') and names precise resources (hardware info, CUDA capability, VRAM, UltraTribe framework status). It clearly distinguishes itself from siblings like benchmark_inference and get_atlas_regions by content, though it does not explicitly name a sibling or state what it is not.

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?

Usage context is implied: call this when you need environment/hardware information. However, there is no explicit guidance on when to prefer this over alternatives, when not to use it, or any prerequisites such as CUDA availability.

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