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

Goes well beyond the annotations (destructive/idempotent/openWorld) by disclosing refusal rules, the doubling guard and allowLargeChange, that the previous budget is returned for undo, and that actual spend can run ~20% over target. These are non-obvious behaviors an agent must know before calling a spend-affecting 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?

Front-loads the action and effect, then the refusal conditions, the safety valve, the undo affordance, and the spend caveat in that order. Every sentence carries distinct information 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 5-param spend-affecting mutation with no output schema, it covers what happens on refusal, how to preview safely, what is returned, and the real-world spend variance. Nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the prose adds real meaning: it explains the allowLargeChange escape hatch and the dryRun preview workflow in context rather than leaving them as bare field docs.

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 ('set a campaign's daily budget') plus the immediate effect. It is clearly distinguishable from the sibling mutation tools like create_campaign_budget and update_campaign_budget, which would create or rename/adjust rather than set a specific daily value.

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 concrete preconditions (standard daily budget only; shared/lifetime/accelerated budgets are refused) and explicitly recommends 'Use dryRun first when unsure.' It does not name a sibling as the alternative for the refused cases, which keeps it from a 5.

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