gmail_reply_draft

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

Annotations declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds real value beyond that: it explains the threading behavior (threadId plus In-Reply-To/References), the recipient restriction, and that user approval is required. It omits any duplicate-draft risk or whether drafts are re-created on repeated calls.

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?

Three tight sentences, front-loaded with the action and the thread behavior, and the sibling contrast is packed into a parenthetical with no filler. Only slight compression cost is that the approval note trails at the end.

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 write tool with no output schema, the description covers the essential behavioral facts an agent needs (threading, single-sender addressing, approval gate). It leaves gaps around cc/bcc semantics and send-as/signature behavior, but the schema documents those, so the definition is largely complete.

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 63%, so several parameters carry their own docs, but the description adds almost no parameter-level detail for the 8 params (send_as, include_signature, cc/bcc are untouched). Notably it says 'Addressed only to the original sender' while the schema exposes cc/bcc, which leaves the agent unsure how those fields interact with that claim.

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?

States a precise verb+resource ('Create a Gmail draft replying to a single message') and explicitly distinguishes itself from the sibling gmail_create_draft by naming the threading mechanism. An agent can tell it apart from gmail_reply_all_draft and gmail_create_draft without opening any 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?

Gives clear context for use ('replying to a single message', 'Addressed only to the original sender'), which implicitly routes multi-recipient replies to gmail_reply_all_draft. It does not name that sibling explicitly or state when-not-to-use, so it stops short of a 5.

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