campaign_delete_preview

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

Annotations already declare readOnlyHint=true, destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that by specifying the blast radius ('cascade inventory') and a precondition ('paused campaign'), which an agent cannot derive from the hints alone.

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 dense sentence with zero filler; the irreversibility and cascade scope are front-loaded. It is efficient, though it stops short of the point where an agent knows the next step.

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 need not be described. However, for a destructive preview in a preview/apply pipeline, the description omits what the preview produces for later use, what happens on expectedText mismatch, and how to proceed to actual deletion — meaningful gaps for this class of tool.

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 75%, so the schema mostly documents profile, adAccountId and expectedText. The description adds nothing about parameters — notably it never explains that expectedText is a guard against deleting the wrong resource, which is the key semantic for safe invocation. 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 (preview) and resource (deletion of a campaign) with scope: 'one paused campaign and its cascade inventory'. The resource name distinguishes it from the delete-preview siblings (ad_delete_preview, ad_group_delete_preview, keyword_delete_preview), though it never names those alternatives explicitly.

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?

Usage is only implied by the word 'preview' — an agent can infer this is the dry-run step before a real campaign deletion. There is no statement of when to choose this over campaign_pause_preview, nor any mention of the follow-up apply step (operations_apply / operations_verify) that the sibling list strongly suggests.

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