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

Annotations already declare destructive=true, idempotent=true and non-readOnly, so the safety profile is covered. The description adds real value by explaining the approval gating (approval_ref and expected_plan_digest are required, and the tool must correspond to the change just confirmed in conversation). It does not explain what happens on a digest mismatch or whether the approval is consumed on a failed call.

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 the scope, followed by the hard prerequisites. Nothing redundant and 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?

With an output schema and rich annotations, the description is nearly complete for a single-entity confirmation step. It clearly ties execution to a prior user confirmation and names the required guard parameters; only failure-mode behavior for the digest/approval check is left unspecified.

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 coverage is only 17% (only currency is documented), so the description should compensate more. It names approval_ref and expected_plan_digest and explains their role as approval artifacts, but their syntax comes only from the schema patterns, and new_value, old_value and entity_name get no explanation anywhere.

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 daily budget of one Meta ad set from current to approved amount, which is more precise than the name alone. It implicitly separates itself from the prepare-side sibling (adsets_prepare_budget_change) and from operations_confirm_adset_bid, but never names those siblings 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?

"Run the change the user just confirmed in this conversation" implies this is the post-approval execution step rather than a preparation or read step. However, it does not say what prerequisite produced the approval_ref/plan digest, when to prefer operations_get_approval, or what to do if the user hasn't confirmed.

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