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

The description adds real context beyond the annotations: the record is persisted as a draft, it lacks an invoice number until completed, and no email is sent. This clarifies the lifecycle of a write that the readOnlyHint/destructiveHint flags cannot express. It stops short of covering duplicate-submission or idempotency risk, even though idempotentHint=false implies repeat calls create separate invoices.

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?

The description front-loads the operation type ("WRITE:") and then gives the draft, finalize, and verify steps in compact sentences with no padding. The trailing "invoice.create." fragment is unexplained backend jargon that adds little.

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 17-parameter mutation with no output schema, the description covers the lifecycle and how to confirm the result. The remaining gap is that the vat_case enum and the gross/net and discount options are left to the schema, which only documents 65% of the parameters.

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 65%, so the baseline is a 3. The description confirms the two required inputs conceptually (customer and line items), but adds no detail on the business-sensitive options such as vat_case, is_gross, or the two discount levels.

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?

The description names a specific verb and resource ("create an invoice") plus the source of the data ("from line items" for "a customer"), which separates it cleanly from fastbill_complete_invoice and fastbill_get_invoice. An agent can identify the tool 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?

It states exactly when to use this tool versus its siblings: use fastbill_complete_invoice to finalize and assign a number, and use fastbill_get_invoice to verify the result. It also adds a negative constraint ("never sent by this tool") that prevents a common misuse.

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