mfc_ca_postVouchers

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

With no annotations provided, the description carries the full behavioral burden and does substantial work: it discloses the user-approval requirement, automatic base64 conversion for file_paths, and the irreversible orphan-voucher consequence of omitting journal_id. It stops short of describing response/error behavior or what happens when journal_id is invalid.

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 short, dense sentences, with the main purpose front-loaded and each clause earning its place. The parenthetical "（公式MCP未提供・要ユーザー承認）" crams two facts into one bracket, which is slightly less structured than ideal but still efficient.

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 mutation tool with no annotations and no output schema, the description covers the essentials: purpose, authorization requirement, the two input modes' behavior, and the critical pitfall. The only notable gap is the absence of return-value or failure-mode information, which matters for confirming a successful attachment.

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 100%, establishing a baseline of 3. The description adds meaning beyond the schema: it explains that file_paths triggers automatic base64 conversion (so the agent need not pre-encode) and warns that omitting journal_id permanently orphans the voucher — a consequence not visible in the schema.

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 states a specific action and resource: "証憑をアップロードし仕訳に添付します" (uploads vouchers and attaches them to journal entries). This clearly differentiates it from sibling write tools like mfc_ca_postJournals (creates journals) and mfc_ca_deleteVouchers (deletes vouchers).

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 clear usage context: it notes the tool is not in the official MCP, requires user approval (要ユーザー承認), and instructs that journal_id should normally be specified. However, it does not explicitly name alternatives or state when-not-to-use it relative to sibling tools.

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