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

The description adds significant behavioral context beyond the annotations: async delivery, approval requirement in Caribooks, inability to unsend, and the need for the record to exist at delivery time. Annotations only indicate a destructive write (readOnlyHint=false, destructiveHint=true), so this additional detail is valuable and not redundant. It does not fully explain the exact status change of 'mark it sent', but the coverage is strong.

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 appropriately structured: the first sentence gives the core purpose, followed by necessary caveats in a logical order. It is slightly longer than strictly needed, but every sentence covers an important behavioral constraint (async, record existence, irrevocability, approval), so the length is justified. The inclusion of a URL for the approval page is a practical addition.

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 tool with no output schema and a simple parameter set, the description covers the essential behavioral context an agent needs: how to handle user confirmation, the async nature, potential delivery failure, and the requirement to inform the user about approval. It does not mention error responses or success indications, but the absence of an output schema and the simplicity of the action make the description sufficient.

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 baseline is 3. The description does not add new meaning to the parameters themselves; it reinforces the confirm parameter indirectly by stating the email waits for approval, but this is not a parameter-level detail. It neither harms nor significantly enhances the schema's parameter documentation.

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 first sentence states a specific action ('Email a sales receipt to the customer as a PDF from QuickBooks Online, and mark it sent') with a clear verb and resource. It also distinguishes itself from sibling 'send_' tools by explicitly naming the sales receipt, so an agent can differentiate it from send_invoice or send_estimate.

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 implies usage through its clear action statement, but it does not explicitly mention alternatives or conditions for when not to use this tool (e.g., 'use send_invoice instead for invoices'). The sibling tools are similarly named, so the agent must infer the appropriate one based on the document type, which is only implicitly stated.

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