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

Adds substantial context beyond the annotations: hourly billing resumes (matching readOnlyHint=false), the operation takes minutes and depends on GPU availability, a NEW public IP is assigned requiring polling, and it requires the servers:start permission plus a free account/MCP key. This is exactly the operational detail an agent needs before spending money.

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-loads the core action and billing impact, then the IP caveat, then bracketed permission/account signals. Dense but every clause carries operational weight; the parenthetical nesting is slightly heavy but not wasteful.

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 no output schema, the description carries return-value burden and does so: it tells the agent to poll get_server until publicIpv4 is populated and describes the wait via publicIpStatus/publicIpNote. Billing, duration, IP change, and auth requirements are all covered for a one-parameter mutation.

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 single serverId parameter is fully documented in the schema (including its source, gpucloud_list_servers), so the description adds no parameter-level information. Baseline 3 is appropriate.

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 (restores) and a precise resource state (a hibernated server), which cleanly distinguishes it from gpucloud_start_server and gpucloud_restore_server_backup without opening either schema. The parenthetical billing note reinforces that this is the hibernation-wake path.

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?

Makes the trigger condition clear (only for a hibernated server) and prescribes the follow-up workflow: poll gpucloud_get_server until publicIpv4 is set, and never reuse the old address. It stops short of explicitly naming start_server as the alternative for non-hibernated servers, so routing is implied rather than stated.

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