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

Annotations already flag readOnlyHint=false and destructiveHint=true, so the mutation risk is covered structurally. The description adds genuinely new behavior: that a preview is returned unless confirm is true, and that the response includes before value, the delta, and monthly impact — valuable for a tool with no output schema. It omits the over-50%-increase guardrail around acknowledge_large_change, which lives only in the schema.

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, action first, then units, then return values, then the safety gate. Every sentence carries distinct information and nothing is repeated from the annotations or schema.

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 mutating tool with no output schema, the description covers the return shape, the dry-run default, and the unit conversion — the essentials an agent needs to call it correctly. Only the acknowledge_large_change precondition is not surfaced in prose, though the schema supplies it.

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 only 40%, so the description must compensate — and it does for the two most confusing parameters: daily_budget_major gets the real-currency-to-micros conversion rule, and confirm gets the preview semantics. customer_id, campaign_id, and acknowledge_large_change are left to the schema, which is a gap but a lesser one.

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 — change a Google Ads campaign's daily budget — with enough scope detail (daily, campaign-level) to separate it from ads_set_bidding_strategy, ads_campaign_bidding, and meta_set_campaign_budget without opening any 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 clear operational context via 'Previews unless confirm is true', which tells the agent the default mode is a dry run. It does not name any alternative tool or state when this tool should be chosen over a bidding/strategy sibling, so it stops short of explicit exclusions.

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