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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that: the blast radius is exactly one ad and one field, and the change is gated by approval_ref plus expected_plan_digest, which signals stale-plan protection. It stops short of saying what happens on digest mismatch or failure.

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, front-loaded with the action and its scope, with no filler. The closing 'Requires approval_ref and expected_plan_digest' mildly duplicates the schema's required list rather than using that space to explain the undocumented parameters.

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?

An output schema exists, so return values need no explanation, and annotations cover the destructive/idempotent profile. But for a destructive mutation with 60% of parameters undocumented anywhere, the description should at minimum explain entity_name, old_value/new_value, and the digest's failure behavior; those gaps matter before invoking a write.

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 carries the full burden, yet it only repeats the two required parameter names already listed in the schema's required array. The three other properties (new_value, old_value, entity_name) are undocumented in both places; 'from current to approved value' only loosely hints at old_value/new_value, and entity_name is never explained.

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: set the reviewed media field of one Meta ad from current to approved value, which is more precise than the name alone. However, it does not distinguish itself from near-identical siblings ads_replace_creative_confirm and ads_replace_creative_prepare, so an agent cannot tell from the description which of the three to call.

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 precondition (a prior confirmation turn) and ties to approval_ref. But in a sibling set containing prepare/confirm/deny triplets for the same resource, the description gives no explicit when-not or alternative routing, leaving the agent to infer the prepare-then-confirm workflow.

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