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

No annotations are provided, so the description carries the full behavioral burden. It adds useful context by saying the invoice is created without a quote, lines are never AI-filled, and sending is a separate step, but it does not disclose permissions, draft status, idempotency, or other mutation side effects.

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 is front-loaded and compact, with three short sentences that each carry useful information. There is no wasted wording.

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?

The description is adequate for a moderate-complexity create tool, especially since it clarifies the no-quote workflow and separate send step. However, with no annotations, no output schema, and low top-level schema coverage, it should say more about job_id usage, invoice state, and key behavioral constraints.

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 low at 17%, so the description should compensate more. It names due date, memo, deposit, and the concept of worker-written lines, but it omits required job_id and tax_rate_id semantics, leaving key parameters to the sparse 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?

The description uses a specific verb and resource: create an invoice. It distinguishes this tool from invoices_createFromQuote by explicitly saying 'without a quote' and clarifies the lines must be worker-written.

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 clearly signals when to use this tool: when there is no quote and the worker has written the lines manually. It also tells the agent to send the invoice with invoices.send, though it does not explicitly name all sibling alternatives such as invoices_createBatch.

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