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

Annotations supply only destructiveHint=true and a title, so the description carries real weight here: it labels the operation as a WRITE, explains precisely what gets added ('a draft to Quipu'), and clarifies the non-obvious constraint that no issue date or number is sent. It doesn't cover permissions, idempotency, or what happens to the draft afterward.

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?

Three short sentences, front-loaded with the verb and resource, then the WRITE marker, then the draft-finalization caveat. No filler or repetition of the schema.

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 7-parameter mutation with no output schema, the description omits what a caller gets back (presumably the draft identifier needed to continue) and what preconditions exist on contact_id or numbering_series_id. The draft-vs-issued distinction is well covered, but the post-call picture is not.

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?

At 71% schema description coverage the schema already documents most fields, so the description's lack of per-parameter detail is acceptable. Its one contribution is negative-space information: it explains why there is no issue-date or invoice-number parameter. Several fields (tags, notes, payment_method) get no guidance in either place.

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 a DRAFT income invoice for a contact') and immediately clarifies the key qualifier, that the result is a draft rather than an issued invoice. This distinguishes it from quipu_get_invoice and quipu_list_invoices, which read invoices rather than create them.

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 implicitly establishes the use case (you want a draft that a human will finalize in the Quipu app) and explicitly bounds the tool's effect ('Quipu does not issue or register the invoice'). It stops short of naming an alternative tool or stating prerequisites, such as whether the contact must already exist.

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