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

Annotations already declare readOnly, idempotent and non-destructive, and the description matches with 'Read-only.' Beyond that it adds genuine context the annotations cannot: results are scoped to the latest completed sync (a staleness signal), payment data is aggregate rather than itemized, and named fields are excluded (Xero IDs, payment IDs, email addresses, message content). It does not describe pagination or error behavior, but for a single-record read that is minor.

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 compact sentences with the resource and scope front-loaded and the exclusions last. Every clause carries information: provenance, payment evidence, safety, redactions. No filler or repetition of the title.

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?

An output schema exists, so return-shape explanation is unnecessary, and the description still covers provenance, aggregation level and redacted fields. The remaining hole is the invoice_id contract and whether the caller must resolve it via search_xero_invoices first, which an agent calling a two-parameter tool genuinely needs.

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 50% and only workspace_id carries documentation, which the description never reinforces or extends. invoice_id is undocumented in both places — the description never says what identifier it expects, how it is obtained, or how it relates to the excluded 'Xero IDs', leaving the most important input ambiguous. With half the parameters lacking meaning, the description should have compensated and does not.

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 ('Return one sales invoice') and pins the data source to the signed-in owner's latest completed SHVL Xero sync, with aggregate recorded-payment evidence called out. That singular framing implicitly contrasts with the plural sibling search_xero_invoices, but no sibling is named outright, so it stops short of a full 5.

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' invoice and the 'latest completed sync' scope suggest this is for fetching a known invoice rather than browsing. There is no explicit when-to-use, no statement that search_xero_invoices should be used to find an ID first, and no exclusion of cases (e.g. bills vs sales invoices) beyond 'sales invoice'.

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