investigate_host

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

Annotations already cover read-only, idempotent, non-destructive safety. The description adds real beyond-annotation context: point-in-time snapshot with no trending, batched reads, and a note that unknown host names produce a teaching error. It does not, however, describe pagination or size/rate characteristics of the merged timeline.

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?

Front-loaded with the core question, followed by the replacement statement, the return shape, the trigger condition, and routing to alternatives. Every sentence earns its place with no repetition or filler.

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 read-only aggregator with no output schema, the description covers what comes back, how to interpret it ('operational language; do not dump it raw'), when to invoke it, and where to go for log-level detail or corrective action. An agent has everything needed to call and use it 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?

Schema description coverage is 100%, so host_name, hours, and target are all documented in-schema (including the default 24h look-back and the teaching-error behavior). The description itself adds little parameter-level detail beyond naming the bundle contents, so the schema baseline of 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?

Opens with a specific question and verb ('one correlated drill-down'), then enumerates exactly what the bundle contains (host state, cluster, VM rollup, datastores, alarms, performance, merged timeline). This clearly distinguishes it from siblings like get_host_performance or get_events, which it explicitly says it replaces.

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 explicit when-to-use ('after get_cluster_health_summary flags a host'), when-not-to-use ('for syslog lines use scan_host_logs'), and routes action-taking elsewhere ('maintenance mode, evacuate belongs to vmware-aiops'). It also names the four tools it stitches together. Nothing is left to inference.

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