campaign_update_preview

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered and there is no contradiction with "preview." The description adds a small amount of context in implying a read-then-preview workflow, but it does not state whether the preview returns a diff, whether it can fail on invalid payloads, or that nothing is persisted — all useful for an agent reasoning about a no-op call.

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 eight-word sentence with no filler and front-loaded, which is efficient. However, the terseness crosses into under-specification; the second clause ("after reading current state") spends words without adding actionable meaning.

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?

An output schema exists so return values needn't be explained, and annotations carry the safety profile. But for a tool with a large nested payload, four required parameters, and numerous specialized preview siblings, the description fails to convey the preview-then-apply workflow or the scope of the update, leaving real gaps.

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 the schema fully documents profile, adAccountId, id, and the deeply nested payload including enum-constrained bid strategy fields. The description adds nothing beyond that, 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?

The description names a verb and resource ("Preview a campaign update"), which an agent can map to a specific tool, but it omits what can be updated (name, status, budget, targeting, bid strategy) and how it differs from the many specialized preview siblings such as campaign_daily_budget_preview, campaign_schedule_preview, and campaign_pause_preview. The phrase "after reading current state" is ambiguous and does not sharpen the purpose.

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?

No when-to-use guidance, no exclusions, and no named alternative. Critically, it never says what to do with the preview result (presumably operations_apply) or why one would choose this general update preview over the field-specific preview siblings. "After reading current state" hints at a prerequisite but never names campaign_get.

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