mfc_ca_postTransactionJournalize

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

With no annotations provided, the description carries the full burden and discloses genuine behavioral traits: it performs a book-writing mutation (帳簿書き込み), requires user approval (要ユーザー承認), and MF auto-completes debit/credit direction, account-side subject, tax classification, and invoice_kind. This goes well beyond a bare 'creates journals' claim.

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 Japanese sentences with zero filler. The purpose is front-loaded, and every clause earns its place: the action, the approval constraint, the required parameter, and the auto-completion behavior.

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 12-parameter mutation tool with no annotations and no output schema, the description covers the essential call-time facts competently. It does not describe the response shape, the approval flow (e.g., pending status or deferred execution), or error/failure conditions, which an agent needs for a complete mental model of this multi-step operation.

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 only 42%, so the description must compensate. It usefully clarifies that transaction_id and account_id are the required inputs and that tax_id, invoice_kind, and other fields are auto-completed by MF. However, it leaves memo, tags, remark, department_id, sub_account_id, and trade_partner_code unexplained, and the auto-completion statement slightly tensions with invoice_kind's schema note allowing experimental values.

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?

States a specific verb-chain and resource: creating journal entries (仕訳) from transaction details (明細), which distinguishes it from siblings like postJournals and postTransactions. The source-scope ('from transactions') and the auto-completion note differentiate it behaviorally, though it never names a sibling explicitly.

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?

Implied usage context is clear: call this when you have a transaction_id and want to generate journals from it, and only account_id must be supplied. However, it gives no explicit when-not-to-use guidance or comparison to the closely related mfc_ca_postJournals sibling, leaving tool routing to inference.

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