send

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

With no annotations, the description carries the full burden and does add useful behavioral detail: attachments must be outbox file paths, a proof payload is returned, and from_identity changes From/Reply-To behavior. However, it does not disclose side effects such as creating a sent message, authentication requirements, or the semantics of idempotency_key, which is a required parameter.

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 short and front-loaded with the core action, then adds two focused notes about attachments and from_identity. Every sentence adds information, though the parameter discussion is slightly unstructured.

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?

Despite an output schema existing, this is a 10-parameter mutation tool with no annotations and substantial schema coverage gaps. The description covers attachments and from_identity but omits guidance on idempotency, account selection, body/html_body relationship, footer, and cc handling, making it incomplete for reliable invocation.

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 must compensate. It explains from_identity behavior and the attachment path restriction, but 8 of 10 parameters remain undocumented beyond their names. Critical fields like idempotency_key, account, body vs html_body, and footer have no added meaning, leaving significant ambiguity.

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?

'Send new mail' states a clear verb and resource, and the phrase 'new mail' distinguishes this from sibling reply/forward tools. It does not explicitly name a sibling to contrast against, but the core purpose is unambiguous.

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 phrase 'Send new mail' implies this is for creating and sending a new outgoing message, which distinguishes it from reply/forward/draft_send. However, the description never explicitly states when to use this tool over those alternatives or any exclusion criteria, leaving some inference required.

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