Send one approved new outbound email

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

No annotations exist, so description must disclose behavior. It mentions automatic RFC 2047 encoding for German/Unicode subjects and support for htmlBody legacy. But it lacks details on sending limits, error handling, or what 'explicit approval' entails.

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?

Five sentences, front-loaded with key conditions (no messageId, threadId usage). Each sentence adds value, though the approval warning could be more specific.

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 10 parameters and no output schema, the description covers essential usage but omits many optional parameters and doesn't explain return values or error scenarios. Missing details on approval process and side effects.

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?

The description adds context for to, subject, body, format, htmlBody, and threadId, which are a subset of 10 parameters. It explains format defaults and encoding, but cc, bcc, accountAlias, chatScope are not mentioned. Schema lacks descriptions, so partial compensation.

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 clearly states it sends a new outbound email for campaigns and cold outreach, distinguishes from siblings by specifying no messageId, and explains the optional threadId for continuing threads.

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 mentions use for campaigns/cold outreach, when to use threadId (campaign email 2+), and warns to not run without approval. However, it doesn't explicitly contrast with the sibling 'multi_gmail_send' tool for replies.

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