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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds that this executes a previously confirmed change and demands an approval_ref and plan digest, but it does not say what happens on a stale digest mismatch, whether approval_ref is single-use, or what a failed confirmation leaves behind.

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?

Two sentences, no filler, with the action front-loaded and the preconditions trailing. Slightly compressed to the point of being elliptical, but nothing is wasted.

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?

A destructive, confirmation-gated mutation with an output schema in place; the description covers the core intent and the two required tokens but omits failure modes and the relationship to the prepare/deny siblings. Adequate to call it, not quite enough to call it safely in edge cases.

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%, so the description should carry the burden. It names both required parameters and hints that expected_plan_digest is a guard against a stale plan, but it is silent on old_value, new_value and entity_name — three of five parameters — leaving the agent to infer that entity_name identifies the campaign and old_value is a concurrency check.

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: set the reviewed status field of one Meta campaign to approved. That distinguishes it from budget-changing siblings such as operations_confirm_campaign_budget and from the prepare-side campaigns_prepare_status_change. The phrase 'reviewed status field ... from current to approved value' is slightly awkward but the operation is unambiguous.

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?

'Run the change the user just confirmed in this conversation' implies the prerequisite step (a prior prepared change plus explicit user confirmation), which is useful usage context. However, it never names the prepare tool the agent should have called first, nor points to operations_deny_approval as the decline path, so the when-not guidance is left to inference.

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