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

Annotations only give the basic safety profile (non-read-only, non-destructive, non-idempotent, closed-world). The description adds critical behavior beyond that: campaign is created PAUSED, confirm=false triggers a dry-run, Google rejects CPC ceilings with OPERATION_NOT_PERMITTED_FOR_CONTEXT, and CTV inventory is on by default. The worldwide-geo incident with '714 clicks in six hours' is exactly the kind of operational hazard an agent needs disclosed.

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?

Long but front-loaded with the core action, then strategy semantics, then the geography hazard. Nearly every sentence earns its place given the mutation's risk profile, though the CPA-ceiling explanation could be tightened without losing the key fact (no cpc_bid_ceiling parameter exists).

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 not be explained. For a high-stakes campaign-creation tool, the coverage of defaults, hazards, follow-up steps, and dry-run behavior leaves nothing an agent needs 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 description coverage is 0%, so the description must compensate, and it largely does: bid_strategy gets three enumerated values with use cases, target_cpa is flagged as required for TARGET_CPA and in account currency, and confirm is documented as dry-run. It does not explicitly describe name/customer_id/daily_budget semantics, though daily_budget is implied by '+ a daily budget'.

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 ('Creates a Demand Gen campaign (PAUSED) + a daily budget') and immediately distinguishes scope from siblings by noting ads/assets are added separately. An agent can tell this apart from create_search_campaign, create_pmax_campaign, and create_demand_gen_ad without opening a schema.

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?

Explicitly names when to use each alternative: MAXIMIZE_CLICKS for a migrated Video Action campaign, manage_bidding_strategies for post-creation strategy changes, set_ad_group_targeting/get_campaign_targeting for geo, and manage_device_targeting for CTV exclusion. It also states what the tool cannot do (no cpc_bid_ceiling, no geo/lang parameters) and why.

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