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

Annotations already declare safe-mutation (destructiveHint=false, readOnlyHint=false), so the description's job is to add flow detail — and it does: immediate effect on decreases, human-visible confirmation code on increases. It stops short of saying what happens when the cap is exceeded or whether a change can be reverted.

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 with the mutation scope front-loaded and the conditional flow second. The telegraphic fragment "Lowering applies now" is slightly clipped but economically conveys a key asymmetry.

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 explained, and annotations cover the safety profile. What remains — the two-step confirm protocol and the immediate-effect asymmetry — is exactly what the description supplies, with no critical gap for a budget mutation.

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 coverage is 100%, so all four parameters are already documented, including confirm's origin in needs_confirm. The description reinforces the confirm workflow but adds no syntax, unit, or format detail beyond the schema; 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?

Names a specific verb and resource ("Change a campaign's daily budget") and implicitly scopes it against the cap tool via "inside the caps". It is clearly distinguishable from siblings like pause_ad_campaign or go_live_ad_campaign, but no sibling is named explicitly and the cap relationship is only hinted at.

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?

Explicitly branches behavior: lowering applies immediately, while raising a live campaign requires the needs_confirm round-trip. That tells the agent when to expect a second call and what to do with the human. It does not cover the failure case (budget outside caps) or when to prefer this over recreating a campaign.

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