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

Annotations already declare non-destructive and open-world, and the description adds meaningful context: it reads current Meta budgets, persists one approval draft, returns approval_ref/plan_digest, and explicitly says 'this call does not change delivery' so the agent understands nothing goes live yet. It stops short of noting auth/permission requirements or draft lifetime.

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?

Four tight sentences, front-loaded with the action and scope, followed by return values, the confirm path, and the alternative. Every sentence earns its place with no filler.

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 mutation-prep tool with an output schema covering return values and annotations covering safety, the description supplies the missing workflow context (prepare vs. confirm, no delivery impact). Only peripheral details such as auth scope and draft expiry are absent.

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?

Reported schema description coverage is 0% at the top level, so the description carries the burden; it conveys the 1-10 item bound and that each entry is a campaign daily-budget change, but connection_context is unexplained in both description and schema. Nested field semantics (currency units, IDs from read results) live only in the schema payload.

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), resource (campaign daily-budget changes), and scope (1-10), and explicitly contrasts itself with both the confirm step (operations_confirm_campaign_budgets) and the generic entities_prepare_update sibling. An agent can distinguish it from campaigns_prepare_budget_change and the confirm family without opening a schema.

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 a clear two-phase workflow: draft now, then apply only after approval via operations_confirm_campaign_budgets. It names an alternative (entities_prepare_update), though the selecting condition ('for new work') is vaguely worded and doesn't spell out when NOT to use this tool.

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