esxi_host_manage

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

The annotations already declare destructive=true, readOnly=false, non-idempotent, so the safety profile is known; the description adds real value by explaining the preview-first protocol, the need for an exact expected_host, dependency confirmation, and the request_id dedup guard against repeated execution. It does not spell out per-action consequences (e.g. what reboot does to running VMs), which keeps it from a 5.

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 action list is front-loaded and the workflow is compressed into two dense clauses with no filler. It is tight, though the run-on second sentence packs several distinct requirements (resource_schema/get, preview, expected_host, switches, dependencies, request_id) without separation.

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 9-parameter destructive host operation with an output schema present (so return values need no explanation), the description covers actions, prerequisite discovery, preview semantics, identity pinning and deduplication. Remaining gaps are the per-parameter meaning of the allow_* flags and acknowledged_vm_ids, which the zero-coverage schema leaves undocumented.

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 0% across 9 parameters, so the description must compensate: it references expected_host, request_id, dry_run preview, and the 'write switches' (allow_disruption / allow_unknown_impact / allow_protected_impact) plus dependency confirmation. However it never distinguishes the three allow_* switches or acknowledged_vm_ids, and the arguments/action payload structure is left unclear, so the gap is only partially filled.

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?

It names the resource (ESXi host) and enumerates the exact eight operations it performs (maintenance enter/exit, reboot, shutdown, lockdown enter/exit, disconnect, reconnect), which clearly distinguishes it from the sibling *_manage tools for network, datastore, storage, service, firewall, etc.

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?

It prescribes a workflow: call resource_schema/get first, rely on the default preview (dry_run defaults true), then execute with precise expected_host, write switches and dependency confirmation. That is strong when-to-use guidance, though it never states when NOT to use it (e.g. use esxi_power_vm for VMs) or names exclusions explicitly.

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