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

Annotations already cover the safety profile (destructive=true, openWorld=true, readOnly=false), so the description's added value is workflow behavior: one-time receipt semantics, idempotency-key scoping, and the automatic linked-draft continuation that prepares but does not execute the next preview. The finer retry/INDETERMINATE guidance lives in the schema parameters rather than here, leaving a small gap against the destructive mutation.

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?

Core purpose is front-loaded in the first sentence, followed by the mutation scope, then prerequisites, with edge behaviors (continuation, sandbox) last. It is slightly redundant with the schema-level description, which repeats the same next-stage-preview guidance, and the closing sandbox sentence is terse to the point of being cryptic.

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, multi-stage workflow tool with an output schema, the description covers the aspects an agent could not infer from structure: confirmation receipt requirements, idempotency across retries, automatic continuation, and sandbox behavior. Return values are properly left to the output schema, so nothing critical 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 description coverage is 100%, so parameter meaning is fully carried by the schema, including planId retry semantics, idempotency-key reuse rules, and the applyContinuation contract. The description only references the receipt and idempotency key in passing, which is the expected baseline when the schema does the work.

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 (executes/applies), the resource (an AD_CAMPAIGN_CHANGE plan), and the exact fields mutated (budgets, states, names), which separates it from prepare_campaign_changes and from apply_campaign_creation. It does not name any sibling explicitly, so the differentiation is inferred rather than stated.

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 'only a confirmed plan' constraint plus the required one-time confirmation receipt and idempotency key make the preconditions clear. It also notes the Review Sandbox variant skips continuation. It stops short of naming alternatives (e.g. confirm_workflow_plan, query_advertising_campaigns) or stating when not to use it.

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