setup_learning_accounts

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

With no annotations, the description carries the burden and does disclose real traits: only the first account is logged in while others queue in import order, a single browser process is reused, credentials are memory-only, and no task completion is claimed. It omits failure behavior and where state_dir-persisted data goes, but the important side effects are covered.

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 core action and the login-first/queue-rest behavior are front-loaded, and each sentence adds information. The phrasing is dense and slightly telegraphic ("optional shared SMTP + per-account notify_email"), but there is little filler.

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?

An output schema exists so return values need no explanation, but for an 8-parameter setup tool with zero schema description coverage the description is too thin: the structure of the required accounts entries and the meaning of execution_mode, browser_mode, state_dir, and session_handoff are all missing, leaving an agent unable to construct the call confidently.

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 0% across 8 parameters, and the description only gestures at accounts (credentials), sender_email/smtp_auth_code (shared SMTP), and notify_email. Rate, state_dir, browser_mode, execution_mode, and session_handoff are never mentioned, and the required `accounts` array has an undefined item shape (additionalProperties: true) that the description leaves entirely unexplained.

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 compound action: collect credentials, optionally configure a shared SMTP sender with per-account notify_email, and log in the first account. That distinguishes it implicitly from siblings like import_accounts (import only) and login_accounts (subsequent logins), though the differentiation is inferred rather than stated by name.

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 precondition ("Start only after the user supplies learning credentials") and routes follow-up work to the alternative ("login_accounts([next_id]) reuses ONE browser process"). It does not contrast with import_accounts or add_parallel_learning_accounts, so the when-not guidance is incomplete.

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