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

Annotations already declare destructiveHint=true and openWorldHint=true, so the write/external nature is known. The description adds context annotations don't carry: the message is sent strictly as the mailbox owner and nobody else, the body must be plain text, and user confirmation is required. These are real behavioral constraints beyond the structured fields.

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 short, front-loaded sentences with no filler: the action, the sender identity constraint, the format constraint, and the confirmation rule. Each sentence carries distinct information an agent needs.

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 destructive, no-output-schema send tool, the description covers identity, format, and the confirmation safeguard, which is the critical safety information. The gap is the undocumented cc/bcc/subject parameters and absence of any error or failure behavior, but the essentials are present.

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's 'plain text only' partly supports the body parameter and 'as the mailbox owner' reinforces mailbox, but cc/bcc/subject semantics remain undocumented in either place, so it only partially compensates.

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 verb and resource ('Send a new email from this mailbox'), and the word 'new' implicitly separates it from the sibling send_outlook_reply. It does not name any sibling explicitly, so differentiation rests on inference rather than an explicit contrast.

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 one concrete usage rule — confirm with the user before calling — which is genuinely useful for a destructive send. However, it never says when this tool is preferable to create_outlook_draft or send_outlook_reply, nor any condition under which not to use it.

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