kv_cache_stats

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

With no annotations provided, the description carries the transparency burden. It indicates a read operation with '[READ]' and lists return metrics, but does not explicitly guarantee no side effects or mention any behavioral traits beyond reading.

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: two sentences, with the purpose front-loaded in the first sentence and parameter explanation in the second. Every word adds value, meeting the standard of efficiency.

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 simple tool (one optional parameter, no output schema), the description covers the purpose and parameter adequately. It lists three return metrics but lacks details on the return format, which is acceptable for a read-only tool with minimal complexity.

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 input schema has 0% description coverage, so the parameter 'target' is undefined in the schema. The description explains it as 'Inference target name from config; omit for the default,' adding essential meaning beyond the schema's bare type definition.

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 starts with '[READ]' and explicitly lists three specific metrics: KV-cache utilisation, prefix-cache hit rate, and preemption count. This clearly identifies the tool's purpose and resource, distinguishing it from sibling monitoring tools like gpu_utilization or request_metrics.

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?

The description implies usage as a read operation for cache stats but fails to provide explicit guidance on when to use this tool versus alternatives like request_metrics or engine_health. No exclusion criteria or when-not-to-use advice is given.

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