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

Annotations only declare it is not read-only and not destructive; the description adds the mechanism that actually matters: a private draft is saved after a Google validate-only pass and a complete affected-resource snapshot, and no change is sent. That tells the agent the call is a reversible staging step rather than a live 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?

Three sentences, no filler, and the purpose plus the non-sending guarantee are front-loaded before the approval instruction. Every clause adds information an agent needs.

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?

Covers the two-phase prepare/confirm lifecycle, validation, and snapshotting, which is the essential context for a staging tool with no output schema. It stops short of saying what the draft contains or how the agent retrieves it for the approval step, which is the one gap for a tool whose return shape is undocumented.

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 33% (only customer_id is documented), and the nested body fields budget_id, amount_micros, and affected_campaign_ids carry no descriptions. The description does add one meaningful semantic — that the campaign list must be the complete set of affected campaigns, not a partial one — but it says nothing about budget_id or the micros unit, so it only partly compensates.

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 (prepare to change) plus the exact resource (shared daily budget) and the scope of the change (the complete explicitly listed set of affected campaigns). It also names the confirm sibling, so an agent can separate this staging call from the sibling google_ads_shared_budget_update_confirm and from the non-shared google_ads_budget_update_prepare.

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?

Gives an explicit workflow rule: show the returned draft for approval before calling google_ads_shared_budget_update_confirm. That is a clear when-to-use and when-not-to-use in one sentence, naming the alternative tool directly.

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