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

Annotations only say destructive=true and non-idempotent; the description goes well beyond them by disclosing the rolling drain-one-node-at-a-time procedure, control-plane-first ordering, refusal of downgrades and minor-version skips, the online/no-ops-in-progress precondition, and that the change is irreversible. That is exactly the operational context an agent needs before invoking a destructive upgrade.

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 action, then target_version format, then the behavioural guarantees and constraints. Three dense sentences with no filler; every clause conveys a fact the caller needs.

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?

Covers the action, preconditions, mechanics, and irreversibility thoroughly, and no output schema exists so return values need not be explained. It calls the upgrade a 'tracked operation' but stops short of telling the agent how to follow that tracking (e.g. via wait_for_execution), which is the one remaining gap for an async destructive call.

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 already 100%, so the baseline is 3. The description earns a bump by adding a constraint the schema omits: target_version must come from the platform catalogue, plus concrete format examples. cluster_id/cluster_name semantics remain entirely to the schema, and the description doesn't clarify how the name/id fallback resolves.

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 (upgrade the Kubernetes version of an Ankra-provisioned self-managed cluster) and scopes it precisely to self-managed clusters, which implicitly separates it from the managed-cluster sibling. An agent can tell what it does and roughly which tool family it belongs to 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?

Gives real preconditions for use: the cluster must be Ankra-provisioned and self-managed, online, with no operations in progress, and the target version must exist in the platform catalogue. However it never names or routes the agent away from the competing siblings (upgrade_managed_cluster, roll_cluster_to_version, upgrade_cluster_agent), so the selection guidance is implicit rather than explicit.

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