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

Annotations already declare destructiveHint and openWorldHint, but the description adds real context beyond them: it says it only uses the stored plan selected by the refs and rejects other operation kinds before reserving anything, and it warns that external Meta state and spend are affected. That is meaningful operational detail.

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 tight sentences, with the approval precondition and the safety guardrail front-loaded. No filler, though the side-effect warning could be more integrated rather than appended.

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?

With annotations covering safety and an output schema covering the response, the description only needs to explain the preconditions and side effects, which it does. Minor gap: the async nature of 'queue' and the role of connection_context are unaddressed.

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 must carry the burden. It explains that approval_ref and expected_plan_digest select and guard the stored plan, adding value, but says nothing about connection_context and doesn't explain the pattern/format constraints.

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?

It states a specific verb and resource ('queue the approved copy of a Meta ad') and clarifies scope by noting it 'rejects other operation kinds.' That helps separate it from the many other operations_confirm_* siblings, though it never names them explicitly.

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?

The 'After explicit user approval' precondition establishes when to call it, and the rejection of other operation kinds implies scope. However, it offers no explicit contrast with close siblings like operations_confirm_ad_copy_update or operations_confirm_ad_grouped_copy, leaving the agent to infer which confirm tool applies.

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