hcloud_firewall_remove_from_resources_action

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

Adds behavior the annotations do not carry: removal is asynchronous and only complete once the related Action with command `remove_firewall` finishes, plus a table of operation-specific 404/422 errors. Annotations already declare destructiveHint=true and openWorldHint=true, so this additional lifecycle context is genuine added value. It stops short of stating what the call returns (presumably an Action object) or that the action must be polled.

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 core sentence and supported-resource list come first, followed by the async semantics and an error table, which is a sensible front-loaded order. There is minor waste in the redundant H1-style title "Remove from Resources" that merely restates the tool name.

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 two-parameter nested body with no output schema, the description covers the mutation semantics, valid resource types, and failure modes well. The main remaining gap is the return contract (which Action is produced and how to poll it) and the fact that `label_selector` entries in `remove_from` are effectively unusable.

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 50%, so the description needs to compensate. It does clarify that resources are plural and that only `server`-type entries with a public interface are meaningful, which is useful given the schema enum also allows `label_selector`. However, it never explains the `id` field or the shape of the `remove_from` array, leaving the nested body to the schema.

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 ("Removes a [Firewall] from multiple resources") and constrains the target set to Servers with a public network interface. The purpose is unambiguous, but it never references the sibling hcloud_firewall_apply_to_resources_action, so the inverse operation has to be inferred from the tool name.

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 when-not conditions: only Servers with a public network interface are supported, and a 422 `firewall_managed_by_label_selector` means the firewall is applied via a label selector and cannot be detached manually. That is real routing guidance, though the description never explicitly points to the apply counter-tool for adding resources.

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