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

Adds substantial behavior beyond the annotation: additive/nothing-overwritten semantics, per-GB billing, and the async state machine (backuping/maintenance -> online) with the exact tool to poll. The only tension is that destructiveHint=true over-generalizes a state-changing, billable operation, while the description clarifies nothing is overwritten; this reads as useful disambiguation of a coarse hint rather than a misleading claim.

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 dense sentences with the core action front-loaded, followed by cost/state caveats and the poll target. Every clause earns its place; no filler or restatement of the title.

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 compensates by explaining what happens after the call (state transitions, how to observe completion via upcloud_get_storage) and the billing implication. An agent has everything needed to invoke and then correctly handle the asynchronous result.

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 100% (both title and storage_uuid are documented with format guidance), so the schema carries the parameter burden. The description adds no parameter-level detail (e.g., title uniqueness or naming implications), making the baseline 3 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+resource+scope: "Take an on-demand, point-in-time backup of a storage device." This is a distinct action not covered by any sibling (the list is dominated by get/list/modify/start/stop), and the UpCloud endpoint footer pins the exact operation.

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?

Clear context for use (on-demand backup) and it routes the agent to the follow-up tool it will need: poll upcloud_get_storage during the async operation. It does not explicitly state when *not* to back up or any quota/limit alternatives, so it stops short of a full 5.

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