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

Annotations only give the generic readOnly/destructive/idempotent booleans; the description adds the substantive fact that configuration and storage are preserved and that the operation is reversible via start_managed_cluster, plus the fail-closed capability gate on non-AKS providers. It does not state what the caller observes on success (state transition timing, confirmation), so it is strong but not exhaustive.

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 short sentences, front-loaded with the action and its mechanism, then the reversibility guarantee, then the provider limitation. No filler and no repetition of the title or schema.

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?

No output schema exists, yet the description covers the key behavioral outcomes an agent needs: preservation of config/storage and the fail-closed path for unsupported providers. It omits anything about the resulting cluster state or how to confirm completion, which would be the remaining gap.

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 both cluster_id and cluster_name are already documented, including the 'optional when a cluster is selected' nuance. The description adds nothing about parameter selection or precedence, so the baseline 3 applies.

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 ('Stop an existing managed Kubernetes cluster') and immediately scopes it with the mechanism ('provider-native deallocation'), which separates it from the generic sibling stop_cluster. Naming start_managed_cluster as the inverse makes the pair unambiguous.

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 names the counterpart tool (start_managed_cluster) and the provider constraint (AKS only, others fail closed), which tells the agent when the call will succeed. It stops short of contrasting stop_managed_cluster with stop_cluster/stop_cluster-style siblings, so the alternative-selection guidance is incomplete.

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