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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantially more: the meaning of ENABLED ('Google applies that type without asking'), the API coverage gap versus the UI, the existence of ui_only_types, and an explicit caution about over-interpreting the result. That is exactly the behavioral context annotations cannot convey.

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-loaded with the action, then the semantics, then the caution — good ordering with no filler sentences. The 'Returns:' block partly duplicates the existing output schema, a minor redundancy, and the paragraphing is a touch heavy for a single-parameter list tool.

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-parameter read tool with annotations and an output schema, the description supplies everything an agent needs: what it returns conceptually, the API/UI coverage caveat, and how to safely phrase findings to the user. Nothing material 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 description coverage is 0%, so the description must carry the burden — and it does, specifying that customer_id is 'numbers only, no hyphens'. That is the one formatting trap for this parameter. It could go further (e.g., that it must be an accessible customer, use list_accessible_customers to find it), but the critical detail is present.

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 ('Lists the account's auto-apply recommendation subscriptions') and immediately defines what a subscription means in this domain, so the agent knows this is a read of recommendation auto-apply settings rather than a general recommendations list. It does not explicitly distinguish itself from the sibling pause_auto_apply_subscription, but the read/mutate split is self-evident from the verb.

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?

Provides real usage context: it warns that this list alone cannot prove auto-apply is fully off and that ui_only_types exist only in the UI, which is precisely the kind of guidance that prevents a wrong conclusion. It stops short of naming alternatives or stating prerequisites (e.g., which auth/scope is needed), so not a 5.

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