Send Email

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

The description goes beyond annotations by detailing two distinct operational modes: cloud mode (SMTP, returns message ID) and local mode (Mail.app, plain text only, no ID). It also notes the immediate, no-draft behavior. These are significant behavioral details not present in the annotations, which only indicate non-read-only, non-idempotent, and non-destructive traits.

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 sentences, each essential: the first states the core function, the second explains mode differences and return behavior, and the third warns about the lack of a draft. No filler words; information is front-loaded and efficiently organized.

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 the tool's moderate complexity (6 parameters, no output schema), the description covers all critical operational aspects: recipients, CC/BCC, HTML, mode-specific behavior, return values, and the immediacy of send. It sufficiently prepares the agent to invoke the tool correctly without needing external documentation.

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 input schema already covers all parameters with descriptions (100% coverage), so the baseline is 3. The description adds value by clarifying comma-separated recipients and especially by noting that local mode only sends plain text, which affects how isHtml and body should be interpreted. This helps the agent understand parameter behavior beyond the schema.

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 the tool's purpose: 'Sends an email immediately from the user's account to one or more comma-separated recipients.' It specifies the verb (sends), resource (email), and qualifies how recipients are specified. It also differentiates from sibling tools like send-message by explicitly focusing on email.

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?

The description gives clear context on when to use the tool (immediate email sending) and importantly warns about the lack of a draft step, which helps with decision-making. It does not explicitly mention alternatives like send-message for chat, but the tool name and scope make the intended use clear enough.

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