get_gpu_vram

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

With no annotations, the description carries the full behavioral burden and does disclose mechanism and a degradation path: it parses nvidia-smi and gracefully falls back on Apple Silicon / integrated display controllers. That fallback disclosure is genuinely useful because it tells the agent the call will not hard-fail on non-NVIDIA hosts. Gaps remain: it never states read-only semantics explicitly, the units of the VRAM figures (MiB vs GB), or what is returned when no GPU exists at all, which keeps it below 5.

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?

Three short sentences, front-loaded with the core capability, then mechanism/fallback, then the usage cue. Every sentence adds something, though 'GPU health' alongside the enumerated VRAM and utilization metrics is mildly redundant phrasing.

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 zero-parameter, no-annotation, no-output-schema diagnostic tool, the description covers what is measured, how it is sourced, how it degrades on non-NVIDIA hardware, and when to call it. Missing only output-shape specifics such as units or the no-GPU result, which the absent output schema would otherwise have supplied.

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 takes zero parameters, so there is no parameter meaning to convey and the baseline is 4. Nothing in the description conflicts with the empty 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?

States a specific verb and resource: 'Checks GPU health, total/used/free VRAM allocation, and utilization,' which tells an agent exactly what is measured. It does not name or differentiate from any sibling, but the resource domain (GPU/VRAM) is distinct enough from get_system_vitals, inspect_port, and the process-cleaning tools that confusion is unlikely.

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?

'Use before starting local LLM/CUDA workloads' gives a concrete triggering context, which is more than most generic diagnostics tools offer. It stops short of explicit exclusions (e.g., when get_system_vitals would suffice instead) or prerequisites, keeping it at a 4 rather than a 5.

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