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

Annotations already declare readOnlyHint, destructiveHint=false, and closed-world, so safety is covered. The description adds meaningful behavior: the default range (1h when omitted), inclusion of a latest reading, the definition of waiting as measured wall-time percentage, and the null case when the host lacks complete same-run readings.

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?

A single dense sentence that front-loads what is measured before the range and use cases. It is slightly run-on, but nearly every clause carries information an agent needs.

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 does the work of describing returned fields (CPU, memory, wait, stalls, latest reading) and the null condition. Combined with annotations covering the safety profile, an agent has enough to call it correctly; only the id parameter remains purely schema-defined.

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 must carry the load. It documents the range enum values and the 1h default (which the schema does not state), but says nothing about the required id beyond what the schema's uuid format implies. Partial compensation only.

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 names the exact resource (a sandbox's measured CPU as percent of vCPUs and cores, resident memory, CPU wait, memory stalls) and the retrieval granularity. It is clearly distinguishable from siblings like runtime_sandboxes_inspect or runtime_sandboxes_process, which are not metrics-focused.

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 gives three concrete use cases: sizing a sandbox, telling whether a process is busy or waiting, and finding what drove a bill. No alternatives are named explicitly, so it stops short of a 5, but the when-to-use context is clear.

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