Auto-apply recommendation subscriptions

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

The annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description still adds real context beyond them: what a subscription actually does (Google applies every new recommendation of that type without a preview), the ENABLED/PAUSED status vocabulary, the rule that an unlisted type is not auto-applied, and the 30-day-modified flag in insights[] for audits.

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?

The purpose is front-loaded in the first sentence and the follow-on detail about no-preview behavior and the unlisted-type rule each earn their place. The trailing Google Ads API documentation URL is boilerplate that adds little, and the sentences are broken across lines mid-clause, which slightly hurts scanability.

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 one-optional-parameter read tool with an output schema and read-only annotations, the description covers what the agent needs to interpret results, including the negative case (unlisted type means not auto-applied). The remaining gap is routing: it does not mention the draft tool that modifies these subscriptions.

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?

There is a single optional parameter and schema description coverage is 100%, with the schema already explaining the dashed-digits format and the configured default. The description adds nothing about customer_id, so the baseline 3 applies.

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?

The opening sentence gives a specific verb and resource: list the recommendation types Google applies automatically. It clearly describes a read of auto-apply subscription state, which is distinct from get_recommendations (individual recommendations). However, it never names the sibling that changes subscriptions (draft_recommendation_subscriptions), so the agent must infer the boundary itself.

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?

Usage is implied rather than stated: the description explains that a subscription applies changes with no preview and that insights[] supports a recurring audit, which hints at when to call it. It never says when NOT to use it, nor points to draft_recommendation_subscriptions for enabling or pausing auto-apply, so the write counterpart is left undiscovered.

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