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

Annotations already declare destructive, idempotent, and non-read-only behavior, so the gap to fill is the safety mechanism — and the description does that by flagging dry-run as the default and the Pro-plan gate. It doesn't explain what a dry-run response contains or what happens if a campaign under CBO is targeted, which keeps it from a 5.

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 short clauses, each carrying distinct information: target, unit, execution default, and entitlement. No filler and the core action is front-loaded.

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, destructive tool with no output schema, the description supplies the critical safeguards (dry-run default, explicit opt-in to execute, plan requirement). Missing only minor details such as expected dry-run output shape and CBO/adset conflict behavior.

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 description coverage is 100%, so both IDs, dry_run, and amount_cents are already documented. The description reinforces the cents/integer>0 convention and the campaign-vs-adset choice, but adds little the schema does not already say — a baseline 3.

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 — changes the DAILY budget of a Meta campaign (CBO) or adset — with unit and scope spelled out. There is no ambiguity about which object is targeted, and no sibling tool overlaps this operation.

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 operating context: default is dry-run, execution requires dry_run:false, and a Pro plan is required. It does not explicitly say when to prefer campaign_id over adset_id, but the schema covers that mutual exclusivity and no alternative sibling exists.

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