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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description adds real operational context beyond them: the one-time nature of the receipt, idempotency expectations, that a linked draft may silently prepare the next preview without confirming or executing it, and that Review Sandbox simulates writes and skips continuation. These are exactly the side effects an agent must know before invoking a destructive write.

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 the gating condition and the effect, then the preconditions, then the continuation and sandbox caveats. Five sentences with no filler, though the final two caveats are dense enough that they read as schema-level detail rather than selection guidance.

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 write tool with a nested continuation object, the description covers the prerequisite chain, the automatic continuation side effect, and the sandbox variant, while the output schema handles return values and the parameter descriptions handle timeout/indeterminate recovery. An agent has enough to invoke it correctly.

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 100% and each parameter already carries detailed guidance (idempotency reuse rules, continuation recovery, receipt scoping). The description only restates that a receipt and idempotency key are required, adding no syntax or semantics beyond the schema, so the baseline 3 applies.

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), a specific resource (an AD_CAMPAIGN_CREATE plan) and the concrete outcome (creates Sponsored Products campaigns). The 'only a confirmed ... plan' scoping plus the sibling set (apply_campaign_changes, prepare_campaign_creation) makes the boundary unambiguous without opening a schema.

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 gates usage on a confirmed plan plus a one-time confirmation receipt and idempotency key, which tells the agent it must call confirm_workflow_plan first. It also carves out the Review Sandbox case. It does not explicitly name the alternative to use for a change vs. a creation, so it falls short of a full when/when-not matrix.

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