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

With no annotations, the description carries the full burden and does most of it: it warns that the app password transits the conversation, that the password is never returned, and — most importantly — that 'WARM-UP STARTS IMMEDIATELY' so the real mailbox will send and receive warm-up mail. It omits whether an existing mailbox is replaced, how to undo (disconnect_client_mailbox exists but is unnamed), and any failure/permission behavior.

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-loads the highest-risk facts (own mailbox, app password through the conversation, warm-up starts immediately) before the reference data. Dense but every clause carries information; the all-caps emphasis is slightly noisy but functional rather than decorative.

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 an 8-param, 6-required connection tool with no annotations and no output schema, the description covers credential format, security handling, host/port reference values, and the immediate side effect. Remaining gap is lifecycle context — replacement of an existing mailbox, reversibility, and what a successful call yields.

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 only 13% (only 'password' documented), so the description must compensate and largely does: it explains the password must be an APP PASSWORD and supplies concrete smtp_host:port and imap_host:port values for Gmail and Outlook, covering four weakly documented required params. It adds little for 'email', 'from_name', or why 'provider' (the one enum) matters.

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 ('Connect') and a narrowly scoped resource ('the user's OWN mailbox for sending'), which separates it from connect_content_account, connect_google_meet and the auth-flow siblings. The 'OWN' qualifier also distinguishes it from reconnect/list/disconnect mailbox tools in the same family.

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?

'prefer asking the user to connect it in the app (Settings → Email Sending) unless they explicitly give you the password' gives an explicit preferred path, an alternative, and the exact condition that licenses this tool. That is the when-to-use-vs-alternative guidance an agent needs for a credential-handling tool.

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