Send an email via Gmail

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

With no annotations provided, the description carries the full burden and delivers richly: it discloses irreversibility ('cannot be undone'), the absence of a draft step, the confirmation prerequisite, the refusal when confirm is missing, and the Gmail authorization requirement. This is exemplary behavioral disclosure.

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 only three packed sentences, front-loaded with the irreversible action and immediately followed by the critical safety rule. Every clause earns its place, covering confirmation, moded behavior, and authorization without fluff.

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 six parameters, no annotations, and no output schema, the description fully specifies preconditions, the confirmation gate, both usage modes, parameter dependencies, and auth requirements. It leaves no ambiguity about how or when to invoke the tool.

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?

Although schema coverage is 100%, the description adds crucial semantics beyond the schema: confirm must be true or the call is refused, to/subject are only required when thread_id is omitted, and subject is ignored in thread replies. These conditional interrelations are not evident from the property descriptions alone.

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 uses a specific verb ('SENDS a real email immediately') and identifies the resource ('authorized Gmail account'), making the tool's purpose unmistakable. It also differentiates from sibling tools like draft_gmail_reply by emphasizing there is no draft step and no undo.

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?

It gives an explicit when-to-use gate: 'Only call this after showing the user the exact to/subject/body and getting explicit confirmation' and states the hard requirement 'must include confirm: true or it is refused.' It also explains the two distinct modes (thread_id vs to + subject), giving clear situational guidance.

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