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

The destructiveHint annotation is already present, but the description goes well beyond it by disclosing that the email cannot be unsent, delivery is asynchronous, the record must still exist, and user approval is required in Caribooks. It also explains a surprising QuickBooks quirk about the email parameter.

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?

Four dense, purposeful sentences with the core action front-loaded. Every additional clause carries a necessary caveat or instruction, and there is no wasted wording.

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 asynchronous operation with no output schema, this is remarkably complete: it covers required email behavior, approval dependency, delivery timing, irreversibility, and a failure mode. An agent knows what to do, what to warn the user about, and what can go wrong.

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 coverage is 100%, so the baseline is 3. The description adds important meaning for the `email` parameter: it is effectively required even though the schema marks it optional with a default, and it explains why. This genuinely helps an agent avoid a known failure.

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?

Opens with a specific action ('Email a purchase order to the vendor as a PDF') and names the exact resource, making it immediately distinguishable from send_invoice, send_estimate, and other send_* siblings. The delivery mechanism and document type are unambiguous.

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 clear context for when this tool is appropriate: emailing a purchase order. It also tells the agent what to convey to the user about the approval flow. It does not explicitly name alternatives or exclusion conditions, but no other sibling serves this exact purpose.

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