winops_perf_system

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context beyond these: the note that CPU sampling blocks for sample_interval seconds in a thread pool (not the event loop). This is important for an AI agent to know because it affects execution timing, and it also clarifies conditional inclusion of network_io in the return format.

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 appropriately sized: a one-sentence purpose, a compact return format block, two example invocations, and a crucial behavioral note. Every section earns its place, and the information is front-loaded with the purpose first.

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 performance snapshot tool with two optional parameters, the description is complete. It covers the return format, shows invocation examples, explains the blocking behavior, and explicitly states the conditional inclusion of network_io. Annotations already cover safety, so no further behavioral disclosure is needed.

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% for both parameters, so the baseline is 3. The description adds value through examples showing typical usage (system() and system(include_network=False, sample_interval=0.5)) and by explaining in the return format that network_io appears only when include_network=true. This clarifies parameter behavior beyond the schema definitions.

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 specific verb ('Snapshot') and clearly enumerates the resources covered: system-wide CPU (per-core), memory, disk I/O, and optionally network I/O. This distinguishes it from sibling tools like winops_perf_process (process-level) and winops_sys_health, making the tool's purpose immediately clear.

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 states it snapshots system-wide metrics, which implies use for system-level performance rather than process-level. However, it does not explicitly name alternatives or state when to prefer this tool over winops_perf_process or system_health_card. The examples show how to invoke it but not when to choose it, so usage guidance is implied rather than explicit.

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