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

The description adds the key behavioral trait that the update is confirmation-gated, meaning the budget is not changed until a later confirmation step. Annotations only state readOnlyHint=false and destructiveHint=false, so this context is value-add. However, it does not disclose what 'prepare' actually does (e.g., validate, create pending operation, any side effects) or require the caller to later confirm.

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?

The entire description is one short sentence with no filler or redundant phrases. It front-loads the most distinguishing information ('Prepare', 'confirmation-gated') but is arguably too sparse to stand alone.

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?

Given the tool's four parameters, zero schema coverage, and the surrounding confirmation-gated flow, the description omits essential context: how to progress from prepare to confirm/deny, what the output contains, and the role of current_daily_budget. It is not complete enough for an agent to invoke this tool correctly in the broader workflow.

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?

With 0% schema description coverage, the description needed to explain the parameters but only clarifies that the update concerns a campaign daily budget, which maps to daily_budget. campaign_id and ad_account_id are self-evident from their names, but current_daily_budget is unexplained – an agent cannot tell why it is optional or what it is used for.

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 identifies a specific action ('prepare'), a resource ('campaign daily-budget update'), and a mode ('confirmation-gated'), which distinguishes it from a direct update tool. It is clear but slightly ambiguous because the tool name says 'update' while the description says 'prepare'; still, the core purpose is understandable.

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?

The phrase 'confirmation-gated' implies this is the preparation step in a two-phase flow, and the existence of overview_update_confirm/deny and other prepare/confirm/deny siblings supports that. However, no alternatives are named, and it doesn't say when to use this vs overview_update_campaign_budgets or the confirm/deny tools.

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