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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-derivable context: source addresses and content are untrusted data and do not constitute sending authority, which is critical prompt-injection guidance for an outbound-send tool.

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 tight sentences with zero padding, front-loaded with the core behavior before the security caveat and the alternative-tool pointer. Every clause carries distinct information.

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?

An output schema exists, so return values need no explanation, and annotations cover safety. The description supplies the authorization/untrusted-data framing and the send_message fallback. What's missing is only the relationship to reply_all_message, which an agent choosing among reply siblings would want.

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 86%, so the schema already documents text, html, labels, attachments, inbox_id, message_id and idempotency_key in detail. The description adds only the implicit-derivation rule (reply recipients and subject come from the source), which the schema's message_id description also covers. Baseline 3 applies.

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 specific verb+resource and scope: 'Reply using the source's reply recipients and subject,' which tells the agent the recipients/subject are derived from the source message rather than supplied. It distinguishes itself from send_message ('Use send_message for overrides') but never mentions reply_all_message, a close sibling whose difference (visible To/Cc inclusion) matters for selection.

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 explicit routing guidance ('Use send_message for overrides') and a clear authorization precondition ('Send only correspondence authorized by the human'). It stops short of an exclusion list or mentioning when reply_all_message is preferred over this tool.

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