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

With annotations present (readOnly=false, destructive=false), the description still adds real context: it creates a persisted approval draft, returns approval_ref and plan_digest, and explicitly does not alter delivery until a separate confirm call. This two-phase, no-side-effect-on-delivery behavior is exactly the kind of trait annotations alone cannot convey.

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, front-loaded with the action and effect, followed by the follow-up dependency and the alternative. 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?

Annotations cover the safety profile, an output schema covers the return refs, and the description covers the prepare/confirm workflow and sibling alternative. Only parameter units are missing, which is minor for a three-field tool.

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 0% and none of the three required parameters (campaign_id, ad_account_id, daily_budget) are explained. Nothing states the currency/unit of daily_budget, the format of the IDs, or that ad_account_id must match the authorized account beyond a passing mention of 'your authorized account'.

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+resource and scope: 'Prepare one campaign daily-budget change', reading current Meta settings and saving an approval draft. The phrase 'one campaign' implicitly separates it from the plural sibling campaigns_prepare_budget_changes, and it names the downstream operations_confirm_campaign_budget, so an agent can place it in the workflow 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?

Explicit sequencing: prepare, then apply only after approval with operations_confirm_campaign_budget, and 'This call does not change delivery' clarifies when it is safe. It also points to entities_prepare_update as an alternative for 'new work', though that alternative condition is vague compared to the rest of the guidance.

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