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

Annotations already declare readOnlyHint=true, so the description earns credit for adding behavior beyond them: 'This call asks no human' tells the agent the call is non-interactive and requires no approval, and 'Default: the last hour' discloses the default time scoping. It does not say anything about cost, sampling granularity, or what happens for containers that no longer exist.

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?

Three short, front-loaded sentences with no filler: resource content first, then default window, then approval behavior. It is perhaps too sparse rather than padded, but every sentence carries signal.

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?

With two undocumented parameters, no output schema, and no explanation of return shape (per-container breakdown vs aggregate), the description leaves real gaps an agent must guess at. The behavioral/metadata side is reasonably covered; the input and output side is not.

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%, so the description must carry parameter meaning and largely fails. 'Default: the last hour' hints that a time-window parameter exists, but since_minutes is never named, its units/bounds (1..10080) are unexplained, and the server identifier's expected format (DNS-style lowercase name) is not mentioned at all.

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 resource (a server's CPU, memory, network, disk, plus container OOM kills, exits and restarts), which is clearly distinct from server_show (state) and server_logs (log text). It does not explicitly contrast with service_metrics though, leaving the server-vs-service scope boundary implicit.

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 implied use case (fetch server-level metrics) is clear from the content, and 'Default: the last hour' gives the time window. But there is no explicit when-to-use vs server_show/server_logs/service_metrics guidance and no conditions given for when not to call it.

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