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

With only non-mutating annotations present, the description carries the behavioral load well: it discloses that disabling removes the update hold from every node and the bastion, that the call is refused while a run is in progress, and that only the members passed are changed (PATCH semantics). These are exactly the side effects and failure conditions an agent needs before calling.

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 walks through enabled, window, and remaining parameters before restating defaults. It is dense and long with several parentheticals, but nearly every sentence adds behavioral detail, so little is wasted.

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?

Despite 9 parameters and no output schema, the description covers defaults, side effects, refusal conditions, window semantics, and partial-update behavior, which together are sufficient for correct invocation. Annotations already establish the mutating, non-idempotent, non-destructive profile.

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 real meaning beyond the schema: it explains the consequence of enabled (platform overrides manual triggering), the meaning of security_lag_days (how long held-back updates may pend), and include_stateful_nodes (draining single-replica volumes / DB pools). It also states the default values, which the schema does not.

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 ('Change an Ankra-provisioned cluster's rolling OS patch policy') and scopes it to Ankra-provisioned clusters, which implicitly separates it from the node-level apply_node_os_policy and the read-only get_os_patch_status. An agent can tell what this does and what domain it governs 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?

Clear context is given for when automatic patching applies (opt-in via enabled, only inside the window, cadence-limited) and it names run_os_patches as the consumer of the setting. It stops short of explicitly saying when to reach for this versus get_os_patch_status or plan_os_patches, so it is clear but not fully routing.

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