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

Goes well beyond the annotations: clarifies "It moves no money" (disambiguating the destructiveHint), documents asynchronous delivery a few seconds after approval, warns that deletion/voiding of the record can block delivery, and explains that the send is irreversible and therefore gated behind user approval. This is exactly the behavioral context annotations cannot convey.

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?

Front-loaded with purpose, then layered with the behavior an agent must know. Every sentence carries a distinct fact (no money moved, async timing, record-must-exist, irreversible/approval-gated) with no filler.

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 no-output-schema mutation tool, the description covers timing, irreversibility, preconditions, and the approval gate thoroughly. It does not say what the call itself returns or how the agent learns the email was actually delivered, which would be the last missing piece for a mutation whose effect is deferred.

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 all four parameters (id, email, company, confirm) are already documented in the schema. The description adds no additional parameter meaning (no format hints, no default behavior for email/company), so the baseline 3 applies.

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?

States a specific verb and resource: "Email the customer a receipt for a payment received, as a PDF from QuickBooks Online." The resource (a Payment) cleanly separates it from the other send_* siblings (send_invoice, send_estimate, send_credit_memo), so an agent can pick it without opening any schema.

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?

Gives real usage context and preconditions: the email is only dispatched after the user approves it in Caribooks, and the agent is told to inform the user of that. It does not, however, name an alternative or state when *not* to use it (e.g., no discussion of the other send_* tools for non-payment documents).

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