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

Annotations only indicate not read-only, not idempotent, not destructive. The description adds that the email reaches a real person immediately, requires user consent, and forbids sending content the lead asked for. This is critical behavioral context beyond annotations.

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 sentences with the primary action first, then two critical caveats. No wasted words.

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?

Covers the essential safety and threading behavior, and schema covers parameters. As an action tool without output schema, it's complete for an agent to call 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 covers all parameters with descriptions, so baseline is 3. The description adds context about the mailbox owning the conversation and threading, which clarifies the mailbox_id parameter's default behavior and the conversation requirement, adding value.

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 (send) and resource (real email to a lead), and clarifies it's a reply via 'threaded onto it.' The phrase 'real email' distinguishes it from drafting, and the sibling draft_reply is implicitly differentiated.

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 instructs to get user agreement before sending, which is a clear usage condition. However, it doesn't explicitly name draft_reply as the alternative when no agreement is given, though the condition implies it.

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