pool_utilization

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds context about the returned metrics and sorting, but does not disclose additional behavioral traits such as error handling, permissions, or data freshness. This aligns with (but does not exceed) what annotations provide.

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 compact and front-loaded, with a summary line, a use-case sentence, and a brief parameter explanation. Every sentence adds value, and the structure is clean.

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?

The description lists the metrics returned (total/available/in-use/error machines and utilization %) and notes sorting, which is sufficient for a simple read-only tool without an output schema. It does not explicitly state the return format (e.g., list of pools), but the per-pool wording makes it reasonably inferable.

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 schema only defines 'target' with type and default, but the description explains it as a Horizon target from config.yaml with the option to omit for default. This fully compensates for the 0% schema description coverage.

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 it reads per-pool capacity metrics (total/available/in-use/error machines and utilization %). The phrase 'am I running out of desktops?' gives the use case, and mentioning machine_list --pool distinguishes it from the more detailed per-machine tool.

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?

It explicitly frames the tool as the high-level utilization view ('am I running out of desktops?') and instructs to drill in with machine_list --pool. This provides clear context for when to use this tool versus the alternative for deeper detail.

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