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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, not destructive); the description adds the crucial non-recoverable detail that currency and time zone can never be changed afterwards, plus a human-confirmation requirement. That is substantive behavioral context annotations cannot express. It still omits permissions/authorization requirements and what happens to a half-configured account.

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, no filler, and the irreversible consequence is front-loaded before the instruction. Every clause carries information an agent needs.

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 creation tool with no output schema and 40% schema coverage, the description covers the critical immutability risk but leaves gaps: the meaning of 'confirm', the origin of manager_customer_id, and what the call returns (e.g., the new customer ID) are all unstated.

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%, and the description meaningfully supplements time_zone and currency_code by framing them as permanently binding choices. However, it never clarifies the undocumented 'confirm' boolean or that manager_customer_id must come from ads_list_accounts, so it does not compensate for the coverage gap.

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 ('Create a new Google Ads account') plus the scoping condition ('for a client under your manager account'), which separates it from sibling campaign/ad-group creation tools. It stops short of explicitly naming the nearest alternative (create_client, ads_list_accounts) that tells an agent where this sits in the onboarding flow.

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 one real prerequisite — confirm currency and time zone with the human before creating — which is genuinely useful guidance. It does not say when to choose this over adjacent tools like create_client or ads_list_accounts, nor does it explain the role of the required manager_customer_id prerequisite call.

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