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

With destructiveHint/openWorldHint already set, the description still adds meaningful context: the mail is sent only as the mailbox owner (identity constraint) and the body must be plain text with real line breaks rather than HTML. It stops short of stating rate limits, irreversibility, or whether the sent message is stored in the mailbox.

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?

Three short imperative sentences, no filler. The core action leads, and the identity, format, and confirmation constraints follow in order of importance.

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 six-parameter, no-output-schema mutation tool, the description covers operation, sender scope, body format, and the confirmation workflow. It omits any mention of cc/bcc semantics or whether an attachment can accompany the send, which is a modest remaining gap.

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 50%: 'to', 'body', and 'mailbox' are documented in the schema while 'cc', 'bcc', and 'subject' are not. The description only reinforces the plain-text body constraint and adds nothing about the undocumented recipients or subject, so it only partially compensates for the coverage gap.

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 names a specific verb and resource ('Send a new email from this mailbox'), and the qualifier 'new' implicitly separates it from send_gmail_reply and create_gmail_draft in the sibling list. An agent can identify the tool's role without opening 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 a concrete precondition — 'Ask the user to confirm before calling this' — which is real operational guidance for an outbound-send tool. However, it never names alternatives, so an agent is not explicitly told to prefer create_gmail_draft for drafts or send_gmail_reply for replies.

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