get_vmstat

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

No annotations are supplied, so the description carries the burden, and it does the most important part: it discloses that sampling blocks for 4 seconds and that the first report is the since-boot average, which is exactly the interpretive trap an agent would otherwise fall into. It does not disclose the SSH connection/auth requirements implied by host/user/key_path/password or any failure behavior, which is the remaining gap.

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?

Front-loaded with the concrete sampling behavior and metric inventory, then the usage directive, then the interpretation caveat about the first report line. Every clause carries information; there is no filler or restatement of the name.

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 exists, so return values need no explanation, and the sampling duration plus the first-line caveat cover the non-obvious behavior. What is missing is the operational context of a remote SSH call (authentication inputs, what happens on connection failure or timeout), which an agent would want before invoking 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?

Schema description coverage is 0% across 7 parameters, so the description needed to compensate and does not: host, port, user, timeout, key_path, password, and accept_new_hostkey are never mentioned. The parameter names are conventional SSH arguments, which limits the damage, but nothing in the description explains credential choice, timeout semantics, or host-key acceptance risk.

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 names a specific mechanism (vmstat), a precise sampling window (4 seconds, 5 reports, 1 second apart), and enumerates the exact metric groups returned (r/b, si/so, bi/bo, in/cs, CPU split). An agent can distinguish this from narrow siblings like get_free_memory or get_disk_usage because the description frames it as a whole-host activity snapshot.

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 THIS TOOL to see what the host is doing right now: swapping, I/O wait, CPU saturation" gives an explicit selection scenario tied to symptoms. It stops short of naming when NOT to use it (e.g., for a single memory or disk figure, where the narrower siblings fit), so it is clear context without exclusions.

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