vm_investigation_bundle

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description reinforces this by stating 'Delegates to the vmware-monitor library (read-only)' and adds performance context with 'Batched, cheap even on large fleets.' It also instructs the agent to 'Explain the result in operational language; do not dump it raw,' which is a behavioral guideline beyond annotations. No contradiction.

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 well-structured and front-loaded: a one-line purpose, a bullet-like list of contents, then batching/read-only info, and finally usage guidance. Every sentence contributes value without redundancy or fluff.

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 complex correlation tool, the description covers the included data types, performance characteristics, read-only nature, and output handling (explain operationally). It also gives usage context and a point-in-time note. With no output schema, the description adequately conveys what to expect and how to present results.

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 100% with clear descriptions for all three parameters (vm_name, hours, target). The tool description does not add parameter-specific details, but it indirectly informs usage via the 'AFTER cluster_health_summary' guidance. Since the schema already documents parameters fully, a baseline 3 is appropriate.

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 one-liner: 'What is happening around this VM?' and then enumerates the exact data correlated: VM state, host, cluster context, datastores, snapshots, alarms, performance, and an event timeline. This precise resource and scope distinguish it from sibling bundles for hosts, datastores, and cluster_health_summary, making the purpose unmistakable.

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 instructs when to use: 'Use this AFTER cluster_health_summary points at a problem VM.' This names the trigger and the preceding tool, and 'Point-in-time' clarifies it is a snapshot. While it doesn't list when not to use, the condition is clear and actionable.

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