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

Annotations only say readOnlyHint=false, openWorldHint=true, and destructiveHint=true. The description adds crucial behavior beyond these: asynchronous delivery, 'mark it sent', record-must-exist caveat, deletion/voiding risk, and approval delay. It thoroughly explains what happens when the tool is invoked.

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?

Every sentence carries essential information: the core action, async behavior, delivery prerequisites, and the user-approval requirement. The structure front-loads the main purpose and then layers critical caveats without waste.

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 mutating send operation with no output schema, the description covers the essential lifecycle, approval flow, and failure conditions. It does not describe return values, but the most important operational facts 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 description coverage is 100%, so the schema already documents id, email, company, and confirm. The description does not add parameter-specific detail beyond the schema, but no compensation is needed because the schema is complete.

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 opens with a specific verb and resource: 'Email an estimate to the customer as a PDF from QuickBooks Online, and mark it sent.' This clearly differentiates it from sibling send_* tools by naming the exact record type (estimate) and the system (QuickBooks Online).

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 gives clear operational context: sending is async, requires user approval in Caribooks, and cannot be undone. It tells the agent to inform the user of the approval step. It does not explicitly name alternative tools like send_invoice, but the resource is unambiguous enough for selection.

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