Delete network load balancer

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

Goes far beyond the annotations: explains that an accepted operation is pending rather than proof of connectivity, that addresses release only after verified cleanup, that the backend enforces ownership/feature availability/2FA locks, and details the in_progress/reason_code/reason_kind polling protocol with next_check_seconds. It also prescribes no auto-retry and key reuse on transport uncertainty. Consistent with readOnlyHint=false, destructiveHint=true, idempotentHint=true.

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?

Front-loaded with purpose and a useful exclusion, then dense but purposeful operational detail. It is long and the polling clause is packed, yet nearly every sentence carries load-bearing semantics for a destructive async operation.

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 destructive, open-world, async mutation with no output schema, the description covers permissions, async/failure interpretation, polling cadence, idempotency recovery, and side effects on addresses. Nothing an agent needs to call it safely is missing.

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 67%; expected_generation has no schema description, but the prose supplies the concept ('at its current generation'). It also adds real meaning to idempotencyKey (preserve it and the unchanged request on uncertain recovery), which enriches the parameter beyond its pattern description.

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+resource (teardown of the network load balancer at its current generation) and distinguishes itself from cancellation/refund siblings. It stops short of explicitly differentiating among the many sibling delete_* tools, but the resource is unambiguous.

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?

Gives clear prerequisites: read current capabilities and owned resource state first, obtain approval for the exact change, and the required networking:read/networking:manage scopes. No named alternative tool or explicit when-not-to-use condition, but the invocation context is well specified.

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