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

With annotations already declaring readOnlyHint=false and destructiveHint=false, the description adds rich behavioral context beyond them: what is re-provisioned vs. powered back on, how snapshot restore works (etcd reset, stale Node/VolumeAttachment cleanup), that a paused cluster keeps its etcd, that provisioning runs as background tracked operations, and that a restore already requested is always kept.

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?

The content is front-loaded and logically ordered, but the description is a dense wall of text whose restore/snapshot semantics are largely repeated in the parameter schema. It could be trimmed substantially without losing decision-relevant information, so it is not appropriately concise.

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 complex mutation with five parameters, no output schema, and background operations, the description covers refusal conditions, restore semantics, paused-cluster behavior, scope variants, and even the shape of the result (state_snapshot_id, trigger, captured_at). Nothing an agent needs to invoke it correctly 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%, so the baseline is 3, but the description exceeds it by spelling out the meaning of each scope enum value ('all' restores the full cluster, 'control_plane' only the control plane and bastion) and giving a concrete use case for the latter. The restore_state and restore_snapshot_id text largely duplicates the already detailed schema descriptions.

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?

The first sentence states a specific verb (start) and resource (a stopped Ankra-provisioned self-managed cluster) and immediately distinguishes it from the managed-cluster siblings by naming the self-managed scope. An agent can tell it apart from start_managed_cluster without opening either 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?

The description explicitly states the refusal conditions (unless the cluster is stopped, a retry of a failed start, or a full start bringing parked workers back) and names restore_state=false as the fresh-start alternative. It also documents the scope='control_plane' use case (verify a change_control_plane result cheaply), giving clear when/when-not guidance.

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