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

Annotations already declare write/non-destructive/non-idempotent, so the bar is lower, yet the description still adds real behavior: the hard precondition rejection and the fact that Plutio computes line totals, subtotal and total server-side. It omits auth/rate-limit context and the shape of the response, but the critical failure mode is disclosed.

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, zero filler, and the 'WRITE:' prefix plus the precondition are front-loaded. Every sentence carries distinct information (mutation type, precondition, side effect, endpoint).

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 two-parameter mutation with no output schema and no annotations gap, this covers purpose, precondition and computation behavior adequately. It could say a bit more about what is returned after the POST, which is the only remaining gap for a no-output-schema tool.

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 baseline is 3. The description earns above baseline by clarifying that totals are derived server-side, which tells the agent that 'amount' is a unit price and that no total fields should be sent — meaning the description reinforces the schema rather than repeating it.

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 opens with an explicit write verb and resource ('put line items on an invoice'), scoped by a precondition ('that has none yet') and traced back to the sibling that creates the invoice. An agent can distinguish this from plutio_create_invoice and plutio_get_document_blocks without reading either 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 names the triggering scenario ('an invoice made with plutio_create_invoice') and an explicit exclusion ('Refuses an invoice that already has an items block'), which prevents a common wrong call. It stops short of naming where to go when the invoice already has items, leaving that case unresolved.

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