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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by explaining the practical consequence: a draft 'is not sent and not due' and 'reaches no one,' so the write has no external effect. It also discloses the auth prerequisite (Cotlet API key with app access). This is exactly the additional 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-loads the core action and ends with the actionable next step. There is mild redundancy between the first two sentences ('Create a draft invoice...' vs 'Creates an invoice in Draft status'), but no filler that would mislead.

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 three-parameter, output-schema-less creation tool, the description covers the required input source, the resulting state, the safety implication, the auth requirement, and the natural follow-up call. Nothing an agent needs to invoke it correctly is missing.

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 client_id, job_id and line_items are already fully documented, including the job_id-vs-line_items fallback ('Without it, pass line_items'). The description's 'from a job or from line items' largely restates the schema rather than adding format or validation detail, so the 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 and resource ('Create a draft invoice') and immediately scopes it ('for a client or a completed job'), which cleanly distinguishes it from the sibling jobber_send_invoice. An agent can tell what it produces (a Draft-status invoice) without opening the 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?

Explicitly names the follow-up alternative ('Check the total, then send it with send_invoice'), giving the agent a clear create-then-send workflow and the condition that selects send_invoice over this tool. The 'runs without asking first' clause also implies it is safe to invoke without user confirmation.

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