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

Annotations declare readOnlyHint=true / destructiveHint=false, and the description confirms 'it changes nothing in Google Ads,' which aligns rather than contradicts. It goes well beyond the annotations by disclosing auth/plan requirements (read_write key, paid plan), the async cost profile (several AI calls per invocation), timing (1-3 minutes), and the explicit anti-retry warning.

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?

Front-loads the operation and its non-mutating nature in the first clause, then layers in the AI behavior, polling, handoff, and constraints. Dense but every sentence carries a distinct decision-relevant fact.

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 an async tool with no output schema, the description fully covers what is returned (draft_id), how to retrieve the result (polling interval), what the result is (ad_groups), and how to consume it, leaving no gap an agent needs to call it correctly.

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 100%, so the baseline is 3. The description adds semantic role beyond the schema by explaining that the landing page content drives keyword grouping and ad text, and that the finished ad_groups flow verbatim into add_ad_groups, but it does not add per-parameter syntax or constraints the schema omits.

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: 'Starts an AI draft of ad groups for an existing Search campaign and returns draft_id at once.' It also distinguishes itself from siblings by naming get_ad_group_draft (polling) and add_ad_groups (the next step), so an agent can place it in the workflow without opening schemas.

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?

Explicit when-to-use and how-to-proceed: poll get_ad_group_draft every poll_after_seconds, preview before passing to add_ad_groups, and do not repeat the call for the same input while a draft is pending or running. Alternatives and the sequencing are spelled out.

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