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

Annotations already indicate destructiveHint=true, so the description doesn't need to restate that. The description adds valuable behavioral context: the Superhuman Undo Send window means sent_at can be up to a minute ahead, and the message leaves the outbox then. It also explains the as_teammate gating on act-on-behalf setting. This goes beyond annotations and helps the agent understand real-world behavior.

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 well-structured with a summary section and a returns section. It front-loads the critical confirmation requirement, then explains the mailbox resolution, then covers the return behavior. Every sentence earns its place, and the formatting with <summary> and <returns> tags makes it scannable.

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 send action with 3 params, 100% schema coverage, and no output schema, the description is complete. It covers the confirmation prerequisite, the return value, the Superhuman timing quirk, the teammate gating, and the deprecated provider param. An agent has everything needed to call this correctly.

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 100%, so the schema already documents all three parameters. The description adds value by explaining the provider param is deprecated and ignored, and by clarifying that as_teammate must be the SAME email passed to draft_reply. This is meaningful semantic guidance beyond the schema.

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 states a specific verb and resource: 'Send a previously created email draft.' It clearly distinguishes this from draft_email and draft_reply by noting it is the send step after drafting, and it explicitly says the mailbox is resolved automatically from the draft log. This makes the tool's purpose unambiguous and distinct from siblings.

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 explicitly says 'Only call this AFTER the user has explicitly confirmed they want to send the draft,' which is a clear when-to-use condition. It also explains that no mailbox arg is needed because the mailbox is resolved from the draft log, and it warns against resending when a user says a just-sent message hasn't arrived. This is strong usage guidance.

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