send_email

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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false), and the description adds what they cannot: irreversibility, the user-confirmation requirement, the conditional Sent-folder append and why it exists (iCloud SMTP does not keep a copy), and the bcc header behavior. These are exactly the behavioral traits an agent needs before firing an irreversible write.

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-loaded with the irreversible-action warning and the sibling routing hint, then the side-effect behavior, then returns, then args. It is longer than most definitions but nearly every sentence carries new information; the args block is a necessary substitute for the 0%-coverage schema rather than padding.

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?

With ten parameters, no output schema, and zero schema description coverage, the description compensates by documenting every argument and explicitly stating the return shape (Message-ID, recipients, saved folder or null). An agent has everything required to call and interpret this tool.

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 description coverage is 0%, so the description carries the full burden and does so: all ten parameters are explained, including source provenance for account ('from list_accounts'), the privacy-relevant bcc note ('never written to headers'), and threading semantics for in_reply_to and references. Nothing is left as a bare name.

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 first clause gives a specific verb and resource (send a new email) plus the transport (SMTP) and immediacy. It also distinguishes itself from the sibling reply_email, so an agent can pick between them without opening either 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 clear precondition ('confirm with the user first') and an explicit alternative for the most likely confusion case ('To answer an existing message prefer reply_email'). It does not cover the other near siblings (forward_email, save_draft_email) or say when not to send at all, so it stops short of full routing guidance.

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