send_email

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals a key behavior: sandbox mode avoids real delivery. However, it does not state that non-sandbox sends are real, irreversible external actions, nor does it mention response behavior, error cases, or required authentication. It adds some useful context but leaves important side effects unstated.

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?

The description is three sentences with no filler. The core action is front-loaded, followed by body type guidance, recipient format, and sandbox usage. Every sentence earns its place and directly aids invocation.

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?

The description covers the main usage patterns but leaves gaps: it does not say what happens if both text and html are provided, whether at least one body is required (schema only requires mailboxId and to), or what the function returns. It also does not mention that non-sandbox sends are real and irreversible, which is particularly important for a 12-parameter sending tool without an output schema.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by clarifying that text and html are alternatives ('either'), that recipients are arrays, and that sandbox=true disables real delivery. This helps an agent choose and fill parameters correctly, exceeding the baseline.

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 opens with a specific verb and resource: 'Send a new email from one of your EngageLab mailboxes.' The word 'new' explicitly distinguishes this from the sibling reply_email, and 'from one of your EngageLab mailboxes' ties it to list_mailboxes. This makes the tool's purpose unmistakable.

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 useful operational guidance like 'Provide either text or html body' and 'Use sandbox=true for testing without real delivery,' but it does not explicitly state when to use this tool versus the sibling reply_email or when not to use it. The usage context is implied through 'new email,' but no exclusions or alternatives are named.

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