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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds real substance: replicas are replaced, secrets and env are re-read, and there is a bounded wait for readiness. Minor ambiguity: it says 'waits up to 40 seconds' while the schema allows waitSeconds up to 45, and it does not say what state is returned if readiness never happens (the schema hints at 'latest state').

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?

Two sentences, zero filler, and the ordering is deliberate: what happens first, then what is excluded, then the safety gate. The approval warning is placed last so it lands.

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 an output schema present, return values need no explanation, and the description covers effect, exclusions, approval, and wait behavior. The remaining gap is failure semantics — what the caller should do if the workload is not ready after the wait window.

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%, so all four parameters (gvc, org, name, waitSeconds) are already documented, including the 'use this instead of polling repeatedly' guidance for waitSeconds. The description adds only the implicit default wait duration, which is not enough to exceed the baseline for fully documented schemas.

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?

States a specific verb (restart) and resource (workload) and immediately defines the semantics: every replica replaced by a fresh one on the same spec, a rolling restart that re-reads secrets and env. This distinguishes it from update_workload and rollback_workload, which would otherwise be plausible confusions.

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 excludes two cases (cron workloads, pointing to start_workload_cron as the alternative; and suspended workloads) and adds a precondition: get approval first. Nothing about when to choose this tool is left to inference.

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