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

The description goes far beyond the annotations (readOnlyHint: false, destructiveHint: true), disclosing partial success per item, the routeToken validity window, that placeholder tokens are invalid, that routeToken does not bypass preview/confirmation, that a call without confirmWrite returns confirmation_required with a preview, that preflight passage is not confirmation, and the counterparty-confirmation scoping. This level of behavioral disclosure — especially the stateful token lifecycle and confirmation semantics — is exactly what an agent needs to avoid misfiring a destructive write.

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 long but every sentence carries operational weight: modes, partial success, token lifecycle, preview/confirmation gating, and counterparty scoping, all front-loaded after the primary action. There is minor redundancy — 'A routeToken does not bypass preview or explicit-confirmation requirements' and 'Passing preflight is not confirmation' overlap in spirit — but each restatement reinforces a different failure mode. No filler or marketing language.

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 complex transactional tool with no output schema, the description covers the critical workflow: token requirements, preview returns, confirmation application, per-item partial success, and counterparty confirmation. The rich input schema covers parameters fully, and the destructiveHint annotation alerts to side effects. The main gap is the absence of detail on the per-item result structure or final success response — 'Results are reported per submitted item' is asserted but the shape of those results is not described, and with no output schema the description bears that burden.

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 schema itself is unusually rich, documenting the three item variants, the confirmWrite gating rule, routeToken semantics, connectionRef reuse, and confirmCounterpartyExplicit conditions. The description reinforces confirmWrite and confirmCounterpartyExplicit behavior in prose but adds little that the schema descriptions do not already state. Baseline 3 applies because the schema carries the parameter-semantics burden effectively.

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 a specific verb and resource — 'Processes cash payments' — and narrows scope with the three modes: 'supplier-ledger, bank-lodgement or analysed-expense mode'. 'Results are reported per submitted item and partial success is possible' signals batch behavior that separates it from the single-item sibling brc_create_cash_payment. However, it never names a sibling or explicitly states 'use this for multiple cash payments in one call', so differentiation from brc_batch_payments and brc_create_cash_payment is left mostly to the tool name.

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?

The description implies the usage context — a routeToken-gated, preview-then-confirm transactional workflow — but never explicitly says when to choose this over brc_create_cash_payment or another batch tool. It states preconditions ('Requires a valid routeToken issued for the matching action workflow', 'Requires confirmCounterpartyExplicit: true') and the two-phase call pattern, which is practical guidance. No alternatives are named and no exclusion conditions are given, so when-to-use vs alternatives is only implied.

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