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

Adds substantial behavioral context beyond the annotations: asynchronous sending after approval, irreversible nature, dependency on record existence, and the explicit instruction to tell the user. These are critical for safe invocation and are not derivable from readOnlyHint/destructiveHint alone.

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 sentences with the core action first, followed by important caveats in order of relevance. Some minor redundancy between 'Cannot be unsent' and the approval explanation, but overall every sentence contributes.

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?

Covers the major behavioral constraints: approval requirement, asynchronous email, non-reversibility, and record existence. Includes a link to the approvals page. No output schema exists, but for a fire-and-forget email action, return value details are not essential.

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 description doesn't add much parameter-specific meaning. It mentions 'to the customer' but doesn't elaborate on the email or company selection parameters. Baseline 3 is appropriate.

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 (email), resource (refund receipt), format (PDF), and system (QuickBooks Online). This clearly distinguishes it from sibling send_* tools, which target different document types.

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?

Explains that the email requires user approval in Caribooks, cannot be unsent, and that the record must exist at delivery. This gives clear preconditions and warns the agent to inform the user. It doesn't explicitly name alternatives, but the resource-specific name makes the intended use unambiguous.

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