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

Annotations already indicate destructive and non-read-only behavior, so the bar for adding context is lower, but the description goes well beyond annotations by disclosing asynchronous sending, irreversibility, approval dependency, and failure conditions such as deletion or voiding preventing delivery. This is highly transparent about real-world side effects.

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 front-loaded with the core action, then gives essential caveats in a sensible order. Every sentence provides necessary behavioral information, including the exact approval URL, without padding.

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 all critical invocation-time knowledge: the action, async delivery, irreversibility, user approval, and deletion/voiding risks. An agent has enough context to invoke this correctly and inform the user appropriately.

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?

The input schema has 100% description coverage for all four parameters, so the schema carries the parameter documentation burden. The description adds general workflow context but does not add new meaning to individual parameters beyond what the schema already provides.

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: email an invoice as a PDF from QuickBooks Online and mark it sent. This clearly distinguishes it from sibling send_estimate, send_purchase_order, and other send_* tools.

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 context: the email is sent asynchronously, requires user approval in Caribooks, cannot be unsent, and depends on the record still existing at delivery time. It does not explicitly name alternatives, but the scope is clear enough for an agent to know when to invoke this tool versus other send_* tools.

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