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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes far beyond them: it details which providers terminate vs power off, that terminating providers snapshot etcd to the backup vault before teardown, that preserve_state=false destroys VM-disk data, that preserve_state=true refuses an uncapturable stop, and that paused/retained resources keep billing. This is exactly the behavioral context a destructive operation needs.

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 purpose and provider list, but it is a single dense paragraph of roughly 300 words that re-explains the 'pause' semantics already documented in the mode parameter schema, and repeats provider lists three times. The information is largely necessary; the packaging is not.

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 destructive, multi-provider, 4-parameter tool with no output schema, the description covers provider-specific stop semantics, state capture/restore, billing implications, distribution constraints, prerequisite ordering with change_control_plane, and the confirmation requirement. Nothing an agent needs in order to call it safely 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 adds distribution/provider constraints not present in the schema (mode 'pause' only for k3s on Hetzner, UpCloud, DigitalOcean; AWS/Scaleway always pause; preserve_state is inapplicable to pause). That extra qualification meaningfully improves correct parameter selection.

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 ('Stop an Ankra-provisioned self-managed cluster') and immediately enumerates the supported providers, so an agent can distinguish it from start_cluster, stop_managed_cluster and delete_cluster without opening any schema. The scope (self-managed, Ankra-provisioned) is explicit.

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 concrete routing advice: use mode 'pause' when the user wants a short stop with everything intact, use the default teardown when they want to stop paying, and 'use before change_control_plane on a single-controller cluster (a 3-controller cluster resizes live without stopping)'. It also requires user confirmation. It does not explicitly contrast with sibling stop/delete tools, so it stops short of 5.

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