cpu_usage

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

No annotations, so the description carries the full burden. It does add real behavioral detail the schema lacks: the metric is aggregate (not per-core) and sampled over a 1-second window, and it returns a severity and recommendation. However it is silent on access requirements, behavior when the server is unreachable, and whether repeat polling is safe.

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?

A single dense sentence, front-loaded with the verb and resource, with sampling scope and output characteristics appended. No filler and nothing repeated from the schema.

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 contents need not be explained; the description correctly focuses on sampling semantics. For a one-parameter read tool this is nearly sufficient, with only the missing usage/alternative guidance keeping it from a 5.

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 100% for the single 'server' parameter ('the inventory server name to check'), so the schema already does the work. The description adds no format or source-of-truth detail beyond it; baseline 3 applies for a 1-param tool with full schema coverage.

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?

Specific verb+resource: 'Report aggregate CPU utilization on a Linux server,' with the 1-second sampling window and severity/recommendation output named. An agent can distinguish it from disk_usage or memory_usage by resource, though the description never explicitly contrasts with those siblings.

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?

Usage is implied (performance triage of a Linux host) but there is no explicit when-to-use instruction, no exclusions, and no routing to alternatives like running_processes or uptime. Adequate but leaves the agent to infer context.

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