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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description adds context: it sends via SMTP, supports attachment types, and is gated by a send_allowlist. It doesn't detail side effects beyond sending, but the send action itself plus the allowlist preconditions is meaningful behavioral context beyond the annotations.

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?

Two sentences with dense, relevant content: the core action, attachment scope, and a clear precondition plus alternative. No wasted words and the critical gating condition is front-loaded.

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?

Given 11 parameters, the schema covers 73%, and the description clarifies the gating condition and the use-vs-draft alternative. It doesn't explain return values, but there is no output schema, and for a side-effectful send action that is acceptable. The description plus schema provide enough for an agent to invoke it correctly.

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 73%, and the schema documents most parameters well (to, attachments, account, html, etc.). The description adds high-level attachment semantics ('existing mailbox attachments, uploaded files, inline content') and the allowlist gating that maps to the recipient parameters. Some parameters like cc/bcc/quote have no schema description, but the tool description compensates reasonably by framing what sending entails.

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?

Description states a specific verb ('sends'), a resource ('an email via SMTP'), and the optional capability ('attachments'). It distinguishes itself from create_draft by naming when sending is disallowed and what alternative to use instead.

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?

Explicitly states when the tool can be used ('only allowed when the owner enabled sending for the account AND every recipient matches send_allowlist') and names the alternative ('Otherwise use create_draft'). This gives clear routing guidance and exclusions.

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