esxi_api_invoke

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds substantial context beyond them: real writes require an env-var write switch and an exact type:moId expected_target, non-VM objects may impact host/shared resources/management link, protected_vm_ids still restricts direct VM refs, no arbitrary Python/shell is executed, and async calls return a task_id. This is a rich disclosure of side effects and safeguards.

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?

Purpose is front-loaded, followed by workflow and then a bullet-style set of constraints and limits. Dense and information-bearing with little filler, though the run-on constraints could be more scannable.

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, 10-parameter, nested-object mutation tool with no schema descriptions, the description covers the critical safety gates and the invocation workflow. It omits meaning for several parameters, but the presence of an output schema means return values need not be explained, keeping it nearly complete.

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 0% across 10 parameters, so the description must carry the burden; it clarifies dry_run sequencing, expected_target's 'exact_type:exact_moId' format, and allow_disruption's role. It leaves method, target, arguments, request_id, acknowledged_vm_ids, allow_unknown_impact, and allow_protected_impact essentially unexplained, so compensation is only partial.

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 concrete verb+resource: advanced typed invocation of server-supported vSphere API management methods, and enumerates the domains covered (network/storage/hardware/service/account/guest/host). It clearly reads as the generic escape hatch versus the typed siblings (esxi_network_manage, esxi_storage_manage, etc.), though it never explicitly names an alternative to route against.

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 an explicit ordered workflow (managers/inventory -> schema/get -> dry_run) and the preconditions for a real call (write switch, ESXI_ENABLE_ADVANCED_WRITES=true, expected_target format, allow_disruption for non-VM objects). It stops short of stating when NOT to use it versus the typed per-domain tools, so it is strong but not fully exclusive.

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