meta_update_entity

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description usefully adds that budget/bid/spend_cap must be in minor units — non-obvious context not in any annotation. However, it never explains the `confirm` gate, the mutability of budgets, or that unspecified fields are left untouched, which is a real gap for a flagged-destructive write.

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 short sentences, front-loaded with the operation and field list, followed by the format constraint and the sibling pointer. No filler; the only waste is that the minor-units caveat could be folded into the field enumeration.

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?

Output schema exists so return values need no explanation, and the annotations cover the risk profile. Still, a destructive write with a required `object_id`, a free-form `fields` bag, and an unexplained `confirm` flag needs more than three sentences before an agent can invoke it confidently.

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 0%, so the description must carry the load, and it does document the allowed keys of `fields` plus the minor-units convention for the numeric ones — meaningful compensation. But `object_id` and especially `confirm` (a boolean gating a destructive write) get no explanation at all, leaving a third of the parameters opaque.

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 (update allowed fields on a campaign, ad set or ad) and even enumerates the mutable fields, so the agent knows exactly what class of operation this is. The enum-of-fields is loose because the actual `fields` parameter is a free-form object, but the intent is unmistakable.

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?

"Prefer meta_set_budget for budgets" is a genuine routing hint with an explicit alternative, which is more than most. But `status` is one of the listed allowed fields and the sibling `meta_set_status` exists — the description gives no guidance on which one to use, and it never says when this tool should not be used.

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