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

Adds useful behavior beyond annotations: the resulting invoice is a draft with the same lines, the conversion has a one-time constraint tied to invoice lifecycle, and it counts toward the free plan document quota. It does not describe permissions or whether the estimate is marked consumed, but the annotations already flag destructive behavior.

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-loads the core action and result, then adds lifecycle and quota constraints compactly. No wasted sentences.

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 one-parameter conversion with no output schema, the description covers the action, result, one-time lifecycle constraint, and billing impact. Minor gaps remain around exactly what is returned or whether the source estimate is altered, but the essentials are present.

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 single parameter is already documented. The description reinforces that the input is an accepted estimate but adds no format or identity details beyond the schema.

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: turning an accepted estimate into a draft invoice with the same lines. This is clearly distinct from generic invoice creation siblings such as create_invoice and create_invoice_from_work.

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 the lifecycle condition: it can be done once while the resulting invoice stands, and again only after the invoice is voided or its draft deleted. It does not explicitly compare against sibling tools like create_invoice_from_work, but the accepted-estimate condition provides clear selection context.

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