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

Annotations only declare write/non-destructive/non-open-world. The description adds real behavioral context: the message is not sent, a human reviews and sends it from the console, and it works even when sending is disabled. The reply-derivation behavior (recipients/subject inherited) is also disclosed, which is more than the annotations carry.

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 tightly packed sentences, front-loaded with the core action and constraint, then the review workflow, then the reply special case. No filler; every clause carries 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?

With no output schema, the description need not explain return values, and it covers purpose, the review guardrail, and reply behavior adequately for a 7-parameter creation tool. Minor omission: nothing about cc/bcc or confirmation of a successful draft creation, but the essentials for correct invocation are present.

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 compensates for the key gap by explaining replyToMessageId beyond its terse schema text: recipients and subject are derived from the original message. It does not cover cc/bcc/body, but for the highest-value parameter it adds semantics the schema does not.

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 concrete verb+resource ('Write a draft into the AgentMail inbox') and immediately scopes it with 'without sending it', which cleanly separates it from the send_agentmail_message / send_agentmail_reply siblings. It does not name a sibling explicitly, but the 'without sending' qualifier makes the distinction unmistakable.

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 a clear conditional for reply mode ('For a reply, set replyToMessageId') and implies the review workflow as the reason to draft rather than send. However, it never states when to prefer a draft over send_agentmail_message or send_agentmail_reply by name, leaving the alternative-selection to inference.

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