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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by stating the metrics are live/real-time and listing which metric families are included. It stops short of saying whether values are instantaneous samples or averages, and what the response shape or units are.

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?

It is a single front-loaded fragment with zero waste, but the terseness crosses into under-specification: a metric-returning tool with no output schema needs more than a noun phrase. Efficient, but not sufficient.

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?

There is no output schema, so the description is the only place an agent could learn what comes back — units, sampling window, per-metric structure — and it gives none of that. For a live-metrics tool it also never clarifies the scope of the 'id' or whether data is current-snapshot only.

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% for the single required 'id' parameter, and the description says nothing about it — not what entity it identifies (presumably a deployment), nor its format. With one undocumented parameter the description needed to compensate and does not.

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 fragment names the resource ('live resource usage') and enumerates the metric families (CPU, memory, disk, network, uptime), so an agent knows roughly what it returns. But there is no verb and no mention that these are metrics for a specific deployment, and nothing distinguishes it from siblings like deployments_get, deployments_logs, or deployments_diagnose.

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?

No when-to-use guidance at all: nothing says to call this for performance troubleshooting versus logs or diagnose, and no alternatives or prerequisites are named. The agent must infer the selection criteria from the name alone.

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