Reply

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

The description adds valuable behavioral details beyond annotations: it replies to the Reply-To address to keep alias mail masked, and clarifies that confirmed=true is required to send. These are not derivable from the readOnlyHint/destructiveHint annotations or the schema alone.

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 core purpose, and every clause adds meaningful information. It avoids unnecessary repetition of schema details.

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 the tool's complexity (11 parameters, no output schema), the description covers the essential behavioral flow (draft vs send, Reply-To masking) without needing to restate schema fields. It omits edge cases like uidvalidity or attachment restrictions, but those are documented in the schema.

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 91%, and the schema already explains draft, confirmed, quote, and other parameters. The description adds a brief note on the draft/confirmed relationship but does not materially augment parameter semantics beyond what the schema provides.

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 'Reply to one message with correct threading,' identifying the exact verb and resource. It distinguishes from siblings like reply_all by specifying 'one message' and from send/forward by the reply context.

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 gives clear context for replying to a single message with threading and explains the draft=true vs confirmed=true modes. It does not explicitly mention alternatives like reply_all for multiple recipients, but the context is sufficiently clear for an AI agent to select this tool appropriately.

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