vm_investigation_bundle

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

Beyond the annotations, it discloses that all reads are batched, that the tool returns a correlated bundle rather than a list envelope, that the event timeline is merged and newest-first, and that the result is a point-in-time snapshot. It also adds an instruction to present output operationally rather than raw. These are meaningful behavioral details the annotations alone do not supply.

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 description is dense but every sentence earns its place: it states purpose, lists contents, gives usage triggers, sets expectations, and issues a clear output instruction. The most important information is front-loaded, and the length is justified by the tool's composite nature.

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 composite read-only tool with no output schema, the description is unusually complete: it enumerates the returned components, states ordering, clarifies batch behavior, warns against trending/acting, and even documents error behavior for unknown VM names. An agent has enough context to select and invoke this tool correctly.

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?

The schema already describes all three parameters at 100% coverage, so the baseline is 3. The description adds useful semantic context by telling the agent where to obtain vm_name ('Get it from list_virtual_machines or cluster_health_summary first') and by tying hours/event timeline to the point-in-time nature of the bundle, which goes slightly beyond the raw schema text.

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?

The description opens with a clear operational question ('What is happening around this VM?') and names the exact function: 'one correlated drill-down.' It lists the constituent data sources (VM state, host, cluster, datastores, snapshots, alarms, performance, event timeline), making it unambiguously distinct from individual sibling tools and from the host/datastore investigation bundles.

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 explicitly tells the agent when to use it ('after cluster_health_summary names a problem VM, or when asked "what's going on with <vm>?"'), when not to use it ('Point-in-time snapshot — no trending'; 'Acting on what you find ... belongs to vmware-aiops'), and what to use instead of stitching lower-level tools together. This is strong alternative-selection guidance.

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