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

Annotations already declare readOnly=false, destructive=true and openWorld=true, so the safety profile is covered. The description adds real value beyond them: it validates the operation kind and refuses mismatches 'before reserving or applying anything', and warns that the call 'Changes external Meta advertising state and may affect spend'. Those are meaningful behavioral disclosures not present in the structured fields.

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 dense sentences with the approval precondition front-loaded, followed by the selection mechanics and the side-effect warning. No filler, though the middle sentence is somewhat packed and could be split for clarity.

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 destructive, open-world mutation with an output schema (so return values need not be described), the description covers the gating precondition, the plan-selection mechanism, kind rejection, and the spend/state impact. Only the connection_context parameter and any idempotency/retry behavior are left unexplained.

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 load. It explains that approval_ref and expected_plan_digest jointly select the stored plan ('Uses only the stored plan selected by approval_ref and expected_plan_digest'), which adds meaning, but it says nothing about the third parameter connection_context nor the digest's role as a tamper/mismatch guard.

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?

The description gives a specific verb and resource ('queue recreation of the approved Meta campaign structure from a prior task'), which an agent can distinguish from the prepare/deny siblings. However it never names the closely related sibling campaigns_recreate_from_task nor explicitly positions itself within the confirm-family, so differentiation is implicit rather than stated.

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?

It clearly establishes the precondition ('After explicit user approval') and that it consumes a stored, previously-approved plan via approval_ref. But it does not tell the agent when to prefer this over campaigns_recreate_from_task or the deny/prepare paths, nor what to do if no approval exists, leaving alternative selection to inference.

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