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

Annotations only cover the safety profile (mutating, idempotent, non-destructive). The description adds the traits that matter: a running server 'restarts once', the change is persistent ('Later redeploys keep the choice'), the billing model for each state, and the precise error codes returned when preconditions fail.

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 verb and resource, and nearly every clause carries distinct information (pricing, preconditions, error codes, persistence). It is a single dense run-on paragraph with parenthetical error codes, which slightly hurts scannability but avoids redundant filler.

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?

For a 2-parameter, no-output-schema mutation tool, the description covers everything needed: preconditions, exclusions, restart side effect, cost implications, and error signaling. Nothing an agent needs before invoking it is missing.

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 coverage is 100% and the schema already documents both parameters including pricing tiers, so the baseline is 3. The description adds meaning beyond that by flagging the need to confirm the costlier alwaysOn=true setting with the user and by explaining what sleeping versus always-on state implies operationally.

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: 'Switch a server ... between always on ... and sleeping when idle', and immediately scopes it as 'in place: no rebuild'. That distinguishes it from rebuild/lifecycle siblings by clarifying no rebuild is needed and only a single restart occurs.

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?

Gives explicit when-to-use (avoid wake-up delay vs. save cost while asleep), explicit when-not (database/cache servers never sleep — 'stop them'), and preconditions ('A stopped or paused server must be started first (SERVER_STOPPED)', refused during builds). It even flags the human-in-the-loop requirement: 'confirm with the user before turning it on'.

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