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

Annotations already declare destructiveHint=true and openWorldHint=true, so the risk profile is partly carried by structured data. The description adds genuinely useful behavior beyond that — which classes of edits increase spend or reach and therefore need chat confirmation — but says nothing about reversibility, permission requirements, partial-failure behavior, or what happens when several fields change at once.

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 editable-field inventory front-loaded and the confirmation rule second. Dense but no filler; the parenthetical '(presence vs interest)' and examples in the confirmation clause earn their space.

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 15-parameter mutation tool with no output schema and destructiveHint=true, the description covers scope plus the confirmation gate, which is the highest-risk behavior. Gaps remain around dry_run/preview expectations (only in the schema) and what a successful response looks like, but nothing essential to invoking it correctly is missing.

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 40% (reason, account, confirm, dry_run, end_date, target_roas are the documented ones), so the description needs to compensate. It does clarify the semantics of location_mode ('presence vs interest'), target CPA, and the network toggles, but leaves campaign_id, add_locations syntax, and remove_location_ids id format unaddressed.

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+resource ('Change campaign settings') and then enumerates the mutable surface: name, end date, location mode, locations, networks, bidding/target CPA. This distinguishes it from update_budget (money) and pause_campaign/set_status (status) by implication rather than by naming them, so it is clear but not explicitly sibling-differentiated.

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?

Gives a concrete conditional rule: spend- or reach-increasing changes (bidding, higher target, more locations, networks) require the user's confirmation in chat. That is real when-to-use guidance, but it offers no when-not guidance and never names the adjacent tools (update_budget, pause_campaign, set_status) an agent might confuse this with.

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