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

Annotations only expose destructiveHint=true/readOnlyHint=false, so the description carries the burden and carries it exceptionally well: it discloses token validity scope, that placeholder tokens are invalid, that a token does not bypass preview/confirmation, the exact two-phase confirmWrite behavior, that preflight is not confirmation, and the counterparty-confirmation scoping. It also reveals the side effect that missing customer contact values remain absent. No contradiction with annotations.

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 a dense single paragraph but well ordered: purpose first, then token lifecycle, then preview/confirm protocol, then counterparty scoping. Nearly every sentence earns its place. Minor redundancy exists with the schema's routeToken and confirmWrite parameter text, but the description stands alone appropriately for a tool this complex.

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?

This is a complex transactional tool (8 parameters, deep nested payload, destructive, confirmation-gated) with no output schema, so the description must cover the operational protocol — and it does, thoroughly: token requirements, the non-confirmed return shape, the preflight caveat, and counterparty confirmation scoping. The one gap is that the success-path return (what confirmWrite true ultimately yields, e.g. the created invoice identifier) is never stated.

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%, so the baseline is 3. The description mostly reinforces what the schema already states about routeToken, confirmWrite, and confirmCounterpartyExplicit rather than adding new per-parameter meaning. It does add one behavioral detail — that a non-confirmed call returns confirmation_required with a payload preview — but does not elaborate on formats, dates, or success-path outputs.

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 opening sentence states a specific verb and resource: 'Creates a sales invoice using generated references and reconciled product, VAT and Sales-analysis lines.' The 'generated references' qualifier captures the distinguishing trait of the gen_ref variant. However, it never names or contrasts the siblings brc_create_sales_invoice (non-generated reference) or brc_generate_sales_invoice_from_quote, leaving the agent to infer the difference.

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?

There is dense operational guidance: a valid routeToken is required, calls without confirmWrite true return confirmation_required plus a preview, preflight is not confirmation, and confirmCounterpartyExplicit must be true. But the description gives zero guidance on when to choose this tool over brc_create_sales_invoice or brc_generate_sales_invoice_from_quote, which are the key selection decisions an agent faces.

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