send_as

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

With no annotations present, the description carries the full disclosure burden and does well: it states the encoding (RFC2822 MIME raw, base64url), the return shape (message id and threadId only), and a security-relevant guarantee ('never tokens'). It does not cover error behavior or sending limits, but the most important behavioral facts are disclosed.

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?

Two dense sentences with no filler: purpose and encoding up front, then required/optional params and return behavior. Every clause earns its place, including the non-obvious 'never tokens' caveat.

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?

For a 7-parameter, no-annotation, no-output-schema send tool, the description supplies the full calling contract: required fields, optional fields, encoding, and return value. The main gap is error semantics (invalid alias, auth failure), but nothing an agent needs to construct a valid call is missing.

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 57%, and the description adds some meaning: it clarifies that at least one of body/html is effectively required despite the schema listing only from/to/subject as required, and it labels cc/bcc as optional. However, it mostly restates schema-provided facts (alias email for from, HTML with or instead of body) and leaves cc/bcc/subject value formats to inference.

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 concrete verb+resource — 'Send mail From a Workspace sendAs alias' — and names the backing API method (users.messages.send). This clearly sets it apart from siblings list_send_as (enumerate aliases) and get_attachment (retrieve a file), so an agent can route correctly without opening the schema.

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 enumerates the exact invocation contract: required from (alias), to, subject, and body text and/or html, with cc/bcc optional. This is clear context for calling. It stops short of explicit exclusions like 'use list_send_as to discover valid aliases first', so it doesn't quite reach a 5.

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