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

Goes well beyond annotations: warns of a brief but real server interruption (shutdown then automatic restart), enforces the at-most-2-manual-backups limit, and documents the single-use 10-minute token. This is rich operational context the readOnly/destructive/idempotent hints alone do not convey.

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 its most important consequence (interruption) before the procedural steps. Dense parentheticals pack in constraints efficiently, though the stacking of caveats makes it slightly crammed.

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 mutation tool with no output schema, it covers action, side effects, limits, prerequisites, auth requirements, and the confirmation protocol. An agent has everything needed to call it safely and correctly.

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%, so the baseline is 3, but the description adds genuine workflow meaning for confirmationToken — the two-call handshake and why the first call is made without it — which the schema's one-line field description 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?

States a specific verb and resource — start a backup of the server's system disk now — and the 'now' scoping clearly distinguishes it from the sibling gpucloud_set_server_backup_policy (policy config) and gpucloud_restore_server_backup (restore). An agent can pick it correctly without opening the schema.

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 states preconditions ('the option must be enabled'), the two-step confirmation flow, and the required permission (servers:backup). The call-without-token → ask-user → call-with-token sequence tells the agent exactly when and how to invoke it.

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