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

Annotations already declare readOnlyHint=false with destructiveHint=false; the description adds the crucial nuance that the only side effect is persisting an internal immutable plan, not mutating ads. It stops short of describing plan lifetime, staleness/expiry, or the confirm step needed before execution.

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?

Three short sentences, no filler, with the nature of the tool and its non-mutating guarantee front-loaded. Every clause carries information.

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 tool with a deeply nested schema, a 20-operation cap, action-scoped snapshot staleness, and a large prepare/apply/confirm sibling family, the description omits the lifecycle (what to call next to confirm or apply) and any mention of plan invalidation. An output schema exists, so return-value detail is not required, but the workflow context is thin.

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% and the nested schema itself documents operations, selectors, action/value shapes, date ranges, and staleness semantics in detail. The description only restates the field domain ('budget, ENABLED/PAUSED state, or name changes'), adding nothing beyond what the schema already provides.

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 and resource: prepares an immutable plan that changes campaign budgets, states, or names, and explicitly says advertising entities are not modified. That distinguishes it from apply_campaign_changes, but it never names the sibling nor distinguishes itself from prepare_campaign_creation or prepare_workflow_draft.

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?

'Separately confirmable' hints at the prepare-then-confirm flow, and 'persists an internal plan without changing advertising entities' implies it is the non-executing counterpart to apply_campaign_changes. But no alternative is named and no explicit 'use this when / not when' guidance is given, so an agent must infer the workflow.

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