get_disk_io_metrics

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

With no annotations, the description carries the full burden and does so well: cumulative-since-boot semantics, read-only source (/proc/diskstats), skipped device classes (loop/ram/zram), and failure behavior ('fatal only if unreadable'). The one notable gap is that it never says rates require differencing two samples, which matters for cumulative counters.

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 dense sentences with zero filler: scope first, then constraints, then routing to the sibling. Every clause earns its place and nothing is buried.

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?

An output schema already exists, so return values need not be documented at length, yet the description still orients the agent to what the counters are. For a parameterless read-only tool, nothing needed to call it correctly is missing.

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?

Zero parameters, so there is no parameter semantics to explain; the baseline for a parameterless tool is 4. The description correctly spends no words on inputs.

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 (per-device disk I/O counters) and enumerates exactly what is returned: reads, writes, sectors, timings. It also names the sibling get_top_io_processes and how it differs, so the agent can disambiguate without opening either schema.

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?

Gives clear use context ('use to attribute I/O across devices') and routes to the complementary sibling get_top_io_processes for process-level attribution. No explicit when-not condition is stated, but the per-device vs per-process split is unambiguous.

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