reply_received_email

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful behavioral context by noting the reply is 'threaded into the same conversation' and that the `from` address must be on a verified domain. However, it does not disclose side effects (e.g., whether the received email is marked as replied), authentication requirements, or any consequences beyond sending the reply. Given the absence of annotations, a more thorough behavioral description would be expected.

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 two sentences, front-loaded with the primary action and threading behavior, followed by the prerequisite constraint. Every word earns its place; the endpoint reference is parenthetical and non-intrusive. It is both concise and well-structured.

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 simple reply tool with no output schema, the description covers the primary purpose and a key constraint. However, it leaves ambiguity about whether `html` or `text` must be provided (or if both are optional), and it does not mention what the response contains. Sibling tools like forward_received_email are not explicitly contrasted, which could lead to selection uncertainty in complex scenarios.

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 schema already documents `id`, `from`, and `subject` (60% coverage). The description adds only the constraint that `from` must be on a verified domain, which is redundant with the schema's 'verified sending address' description. It does not clarify the relationship between `html` and `text` (e.g., whether at least one is required) or add semantics for those parameters. With moderate schema coverage, the description's contribution is minimal.

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 action ('Reply to a received email's sender') and the resource (received email), and distinguishes it from siblings like forward_received_email and get_received_email. The mention of 'threaded into the same conversation' adds a specific behavioral nuance that further differentiates it from a fresh email send.

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 provides clear context: it is a reply operation threaded into the existing conversation, and it requires the `from` address to be on a verified domain. It does not explicitly name sibling alternatives (e.g., forward_received_email) or state when NOT to use it, but the action is unambiguous enough that an agent can infer the appropriate use case.

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