vsan_capacity

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

The readOnlyHint=true annotation already signals a safe read operation. The description adds behavioral specifics: returns vsan_enabled=false with an explanatory message when vSAN is not enabled instead of erroring, and errors only if the cluster name is not found. This goes beyond the annotation by clarifying error semantics and edge-case behavior.

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?

Each sentence earns its place: summary, return format, edge-case behavior, sibling references, safety note, and parameter specifics. No redundancy or filler. The structured Args section is not verbose.

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?

With no output schema, the description compensates by enumerating the exact return fields: cluster_name, vsan_enabled, datastore_name, total_gb, used_gb, free_gb, usage_pct. It also covers error conditions, non-vSAN fallback behavior, and alternative tools. This is a complete picture for a read-only capacity query.

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%, so the description carries the burden. It explains that cluster_name must be 'exactly as shown in vCenter' and errors if not found, and target is an 'Optional vCenter/ESXi target name from config.' This provides semantic guidance the schema omits.

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 '[READ] Get space usage of a cluster's vSAN datastore for capacity planning.' It clearly identifies the specific operation (get space usage), the resource (vSAN datastore), and the scope (cluster). It further distinguishes itself from siblings by pointing to vsan_health for disk-group layout and list_all_datastores for non-vSAN datastores.

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 this tool: for vSAN datastore capacity planning. It directly names alternatives: 'Use vsan_health for disk-group layout and host details; use list_all_datastores for non-vSAN (VMFS/NFS) datastore usage.' Also notes 'No side effects,' giving context on safe usage.

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