host_investigation_bundle

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

Annotations already state readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds rich behavioral detail: what data is collected and correlated (state, cluster, VMs, datastores, alarms, performance, event timeline), batching, and aggregation. No contradictions.

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?

Well-structured with READ tag, bullet-like list of contents, usage instructions, and parameter details. Every sentence is informative without redundancy.

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?

Covers purpose, inputs, and usage well. No output schema, so description could be more explicit about return format, but it hints at operational language and aggregated data. Slightly incomplete.

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%, but the description explains each parameter: host_name (exact name, teaching error, source), target (optional, default null), hours (look-back window). Adds significant meaning beyond 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?

Description starts with '[READ]' and specifies 'correlated drill-down' around an ESXi host. It clearly distinguishes from sibling tools like cluster_health_summary and datastore_investigation_bundle.

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?

Explicitly states 'Use this AFTER cluster_health_summary flags a host, or when the operator asks...' and notes it's a point-in-time snapshot. Provides clear context but doesn't exhaustively list when not to use.

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