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

With no annotations provided, the description carries the full behavioral disclosure burden and does so exceptionally. It explicitly states that billing is the only applied setting, everything else reports 'unchanged', unapplied values are named in warnings[], two brands on one key resolve to the same account_id, and 'advertiser' is refused with a reason.

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 description is long but tightly organized with clear sections: what it does, what it does NOT do, billing behavior, read-only behavior, when to use, returns, and an example. Every sentence earns its place, and the most important caveat is front-loaded immediately after the purpose statement.

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?

This is a complex tool with nested objects, no output schema, and no annotations. The description fully compensates by documenting return fields, giving a concrete example, explaining accepted and refused billing values, and clarifying the one-account-per-key constraint and its consequences for the agent's decisions.

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 67% and the schema already documents several fields, but the description adds substantial meaning beyond it: the two account entry shapes, which settings are persisted vs ignored, how billing values map to invoicing relationships, and how idempotent replays behave. The billing parameter especially gains semantic depth that the enum alone cannot convey.

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 opens with a specific purpose: 'Establish or confirm the account behind this credential.' It then actively distinguishes itself from provisioning by stating it does not create a new account and that per-brand separation is handled by a separate registration endpoint, so an agent can clearly tell this from setup_billing, list_accounts, and register_partner.

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?

A dedicated 'WHEN TO USE' section lists concrete triggers: account setup, declaring invoicing before create_media_buy, and confirming account_id/status before create_media_buy. It also tells the agent when not to use it, namely when per-brand separation is needed, and points to the registration alternative.

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