vsphere_get_performance

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

The description enriches the annotations (readOnlyHint, idempotentHint, destructiveHint) by explaining that counters come back 'summarised (latest, average, minimum, maximum),' that 'realtime' uses 20-second samples, and that counters use a 'group.name.rollup' format. It also notes the default behavior for counters. This adds substantive behavioral context without contradicting the annotations.

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 concise and well-structured. It leads with a one-sentence purpose, adds a brief note on interval semantics, and then lists parameters in a clear Args block. Every sentence provides necessary information—no filler or redundancy.

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 (5 parameters, multiple intervals, counter formats), the description is complete. It covers parameter semantics, return summarization, interval behavior, and default counter set. An output schema exists, so not detailing the exact return shape is acceptable. No gaps are evident.

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 input schema has no descriptions for its properties (0% coverage), but the description compensates thoroughly. It explains 'entity' accepts a name, managed object id, UUID, or inventory path; 'entity_type' is 'vm' or 'host'; 'interval' enumerates the valid values; 'samples' retrieves most recent first; and 'counters' uses 'group.name.rollup' form with a default standard set. This fully compensates for the lack of schema descriptions.

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 CPU, memory, disk and network performance counters for a VM or host,' which clearly specifies the action (read), the resource type (performance counters), and the targets (VM or host). This distinguishes it from sibling tools like vsphere_get_vm or vsphere_list_tasks, which serve different purposes.

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 clear context on when to use the tool by explaining the available intervals (e.g., 'realtime gives 20-second samples for roughly the last hour; the rollup intervals cover longer periods') and how counters work. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls just short of a 5.

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