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

Annotations already declare non-read-only, idempotent (idempotentHint=true) and destructiveHint=true, and the description adds real context: it changes nothing in Google Ads, it is a no-op for an already-active account, and consuming a plan slot is effectively irreversible. The one gap is that it never explains what the destructiveHint=true aspect actually destroys, so an agent must infer that the loss is the plan's account allowance rather than data.

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?

Four compact sentences, front-loaded with the action and then the trigger, the failure mode, the side effect and the format. Every sentence carries distinct information; the quoted UI strings make it slightly dense to parse but are functional.

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 state-selection tool with no output schema, the definition covers trigger, side-effect scope, idempotency, limit behavior and ID formatting. What it omits is what the call returns on success, which matters modestly since there is no output schema to fall back on.

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?

With schema coverage at 100%, the schema already documents customer_id, but the description adds meaning the schema lacks: the mc:<account_id> form for Merchant Center accounts and the fact that the value is taken verbatim as the notice supplies it. Fields-from-schema aside, that prefix rule is the kind of detail an agent would otherwise get wrong.

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 description states a specific action and resource: it takes a customer_id and makes that account the plan's selected account, and it names the 'Account choice:' prompt as the trigger. It also carves out the Merchant Center variant via the mc: prefix. It does not name a sibling tool to contrast against, though list_accounts is referenced only indirectly through the 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?

It gives an explicit trigger ('Call it after a tool answered "Account choice:" and the user picked this account') and an explicit failure condition ('Once the plan's accounts are taken there is no switching: another account answers "Plan limit:"'). That combination tells the agent both when to call and when calling is futile, which is more than most definitions offer.

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