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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuine value by enumerating the returned fields (payments, credit notes, product/service lines) in the absence of an output schema, but says nothing about auth requirements, error behavior for a missing invoice, or pagination/size of the result.

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?

Two compact sentences plus an endpoint reference, with the payload contents front-loaded. The opening noun phrase lacks a verb, so it reads as a field list rather than a stated action, but nothing is padded or wasted.

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?

With no output schema, the enumeration of returned data is the key compensating detail, and it is present. What remains thin is behavioral context around failures and identity resolution (GUID vs number precedence), which matters for an open-world lookup 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 description coverage is 100%, and the description's 'Takes the invoice GUID or its number' restates the schema field description almost verbatim rather than adding format hints (e.g., typical invoice number pattern). With a single fully documented parameter, the baseline 3 applies.

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 states the resource (a single invoice/sale) and enumerates the payload it carries (client, status, payment terms, totals, lines), which is specific. The implied verb is 'retrieve one' rather than list, which distinguishes it functionally from list_invoices, but sibling tools like get_order and get_quote are never named or differentiated.

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?

Usage is only implied: 'One sale' signals a single-record fetch in contrast to the list_* siblings, and the GUID-or-number note hints at lookup by either key. There is no explicit 'use this when…' statement, no exclusion of alternatives such as list_invoices, and no mention of what to do if the identifier is unknown.

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