datastore_investigation_bundle

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

Beyond annotations (readOnlyHint, etc.), the description discloses batching of reads, aggregation within the tool, a teaching error for unknown names, and that it is a point-in-time snapshot. This adds significant behavioral context.

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 with a clear lead, bullet-like list of inclusions, usage guidance, and parameter explanations. Every sentence adds value, and it is front-loaded with the core purpose.

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?

Given the tool's complexity and no output schema, the description adequately explains what the tool returns by listing components. It also provides context on error handling and operational language. The parameter descriptions are thorough, making the tool complete and actionable.

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?

With 0% schema coverage, the description fully compensates by detailing each parameter: datastore_name (exact name, teaching error, suggestion to get from list_all_datastores), target (optional, default if omitted), and hours (default 24). This adds crucial 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?

The description clearly states the tool's purpose as a 'correlated drill-down' for a single datastore, listing specific components (capacity, hosts, VMs, alarms, events). It distinguishes from siblings by explicitly mentioning when to use it after cluster_health_summary and by noting that per-datastore latency is separate.

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?

The description provides explicit usage guidance: 'Use this AFTER cluster_health_summary flags storage pressure, or when the operator asks "what's going on with datastore <x>?"' It also clearly states what is not included (per-datastore latency) and that it provides a point-in-time snapshot with no trending.

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