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

Annotations already mark destructiveHint=true and readOnlyHint=false, and the description builds richly on this: it discloses merge-not-replace semantics, that placeholder tokens are invalid, that a routeToken does not bypass preview or confirmation, that a call without confirmWrite returns confirmation_required with a payload preview, and that passing preflight is not confirmation. No contradiction with the annotations; all claims are consistent with a destructive two-phase 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?

Opening sentence front-loads the core purpose (verb+resource+merge semantics), followed by the mergeable field list and then token/confirmation behavior in logical order. Every sentence carries information, though some confirmation rules are repeated in the schema's confirmWrite description, creating mild redundancy.

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 destructive, 7-parameter transactional tool with nested objects and no output schema, the description is largely complete: it covers the merge field set, token validity and routing scope, the two-phase preview/confirm contract, and the non-confirmed response shape. The main gap is that the sucess response after confirmWrite is not described, which an agent would need to confirm completion.

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, but the description adds real value: it enumerates the exact mergeable fields (total, entryDate, procDate, supplierId, acCode, note, ledger, discount, bankAccountId, bankAccountCode, lodgement, analysisCategoryId, accountCode, description), which matters because the updates/payload objects are open-ended additionalProperties. It also clarifies routeToken and confirmWrite behavior beyond their schema descriptions, pushing this above baseline.

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 gives a specific verb and resource ('Updates an existing Cash Payment') and adds a precise mechanism ('merging supplied fields onto the current record'). The 'existing' phrasing and merge semantics distinguish it from create/delete siblings, though it never names an alternative tool explicitly, which would be needed for 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?

The description provides strong workflow context ('token remains valid through lookup, preview and the permitted transaction', 'confirmWrite: true applies the previewed change after explicit confirmation') that tells the agent how to sequence calls. However, it never states when to prefer this tool over alternatives such as brc_create_cash_payment or brc_delete_cash_payment, leaving alternative routing implicit. Justified as clear context without exclusions.

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