Update invoice

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

Annotations only declare the generic write profile (readOnly=false, destructive=false, idempotent=false), while the description adds real behavioral context: patch semantics rather than overwrite, no customer notification on status change, and a business rule that the system requires a due date on every change. The parenthetical explaining that 'submitted' means sent to the customer and permits payments is meaningful domain state information.

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 short sentences, front-loaded with the verb and affected fields before the caveats. The status enumeration could have been left to the schema, but the added gloss on 'submitted' makes it earn its space.

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 mutation tool with no output schema, it covers the essentials an agent needs to call it correctly: partial update, no side-effect email, and the due_date precondition. It does not say what is returned or whether status transitions are validated (e.g. paid back to draft), which are the only notable omissions.

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 low (20% — only invoice_id is documented), so the description must compensate, and it does well for the two hardest parameters: it lists all six status values with meaning for 'submitted' and states the due_date requirement. It adds nothing about invoice_date or description beyond naming them as updatable, which is the remaining gap.

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 verb (changes) plus the exact resource and the four mutable fields, so the scope of the write is unambiguous. It also implicitly separates itself from the sibling send_invoice by stating that no email goes out.

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?

Explicitly states partial-update semantics ("Sets only the fields you pass") and names the alternative tool for the excluded behavior ("Nobody is emailed. send_invoice does that."). It also flags a hard precondition: due_date must be included if the invoice has none, which is exactly the kind of routing an agent needs.

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