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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: default window of 30 minutes, hard cap of 360, ~30-second sample cadence, oldest-first ordering, and the meaning of gaps (asleep or starting). It also discloses units (permille, divide by 20 for ms/tick, 1000 = lagging), which is exactly the kind of behavior an agent could not infer from structured fields.

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 sentences, front-loaded with what is returned and the default/cap, then per-point field semantics, then the intended use. No filler; even the units-conversion parenthetical earns its place because it prevents a misinterpretation of "load".

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, but the description fully specifies the shape of each returned point (time, memory, tick load, peak players), the ordering, and how to read gaps and lag values. An agent can call this correctly and interpret results without further documentation.

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?

The schema marks 0% description coverage per context signals, so the description carries the burden and does: it states the default (30 minutes) and cap (360) for the window parameter and explains the sample interval that makes that window digestible. It says nothing about the required serverId beyond what the schema itself documents, which is the only gap.

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 (returns load samples for a server over a recent window) with the time range and sampling cadence spelled out, so the agent knows exactly what it fetches. It stops short of differentiating itself from the ambiguous sibling getServerUsage, which sounds like it might return overlapping CPU/memory data.

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?

Explicitly frames the use case: "Use it to explain when and why a server lagged." That is strong positive guidance for when to call it. There are no exclusions or named alternatives (e.g., getConsoleLogs for error text, getServerUsage for plan/quota data), so the agent has no routing help when the question isn't about lag.

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