gpu_utilization

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

The '[READ]' prefix indicates the tool is non-destructive, which is a key behavioral trait. However, with no annotations present, the description carries the full burden of disclosure. It does not mention authentication requirements, rate limits, or whether the data is live or cached. For a simple read tool, this is adequate but minimal.

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?

The description is extremely concise: one sentence for purpose and one line for the parameter. No redundant words, and the most critical information (read nature, per-node output) is front-loaded. Every sentence earns its place.

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 the tool's simplicity (1 optional parameter, no output schema), the description provides sufficient context: it states the tool returns per-node GPU count, utilization percentage, and memory usage. It does not describe the format or structure of the output, but the listed fields give a clear picture. Adding a note about whether the output includes all nodes or a specific node would improve completeness.

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?

Schema description coverage is 0% (the 'target' parameter has no description in the schema). The description compensates by explaining that 'target' is an optional inference target name, defaulting to the default. This adds meaningful context beyond the schema's type-only definition. A slight improvement would be to mention possible values or where to find the config.

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 clearly states it is a READ operation providing per-node GPU count, utilization percentage, and memory usage. It is specific about the resource (GPU utilization) and distinguishes itself from many sibling tools that deal with models, queues, or engine health. However, it could be more precise about whether 'utilisation %' refers to per-GPU or per-node average.

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?

No explicit guidance on when to use this tool versus alternatives like 'kv_cache_stats', 'queue_depth', or 'engine_inventory'. The description does not mention prerequisites, such as requiring a running inference target, or when to omit the 'target' parameter. The '[READ]' prefix hints at non-destructive use but does not provide clear usage context.

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