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

Annotations already flag destructiveHint=true, and the description adds concrete context by stating 'reaches a real person immediately and cannot be undone' and requiring a connected mailbox. This goes beyond the annotation's generic destructive flag to describe the irreversibility and delivery guarantee.

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 no filler. The main purpose is front-loaded, and the key behavioral warning and parameter usage are concisely stated.

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?

The description covers the action, prereqs, and parameter behavior for half the parameters, but it omits the purpose of prospectId and linkedinUrl, and does not mention expected outcomes or errors. For a simple mutating tool, this is a notable gap.

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 descriptions cover body and subject (50% coverage), and the description clarifies that omitting them uses the saved draft. However, prospectId and linkedinUrl have no descriptions in the schema or the tool description, leaving their role ambiguous for identifying the recipient.

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 it sends an email to a prospect, identifying the channel (email vs LinkedIn) and the action (send). It differentiates from sibling tools like draft_email and send_linkedin_message by specifying the connected mailbox and real-time delivery.

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 provides a prerequisite (connected mailbox) and explains when to omit parameters to send a draft, but it does not explicitly state when to use this tool versus alternatives like draft_email or send_linkedin_message. The guidance is mostly implicit.

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