mf_delete_billing

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

With no annotations, the description carries the behavioral burden and does disclose the critical trait that the operation is irreversible ('元に戻せない'), which is exactly the destructive-behavior fact an agent must know. It omits auth/permission requirements and any cascade or side-effect detail, but the irreversibility disclosure is the highest-value item and it is present.

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?

Two tight sentences: the action comes first, followed immediately by the safety-critical warning. Zero filler and the danger signal is front-loaded where the agent will read it.

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 single-parameter, no-output-schema delete tool, the description covers the action, the irreversibility, and the required confirmation step, which is sufficient to invoke it correctly. Remaining gaps (auth requirements, cascade effects) are minor.

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% (billing_id documented as 請求書ID), so the schema already carries all parameter meaning. The description adds no syntax, format, or sourcing detail about billing_id, so baseline 3 is appropriate.

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 ('請求書を削除します' = deletes an invoice) and the exact resource, which distinguishes it cleanly from mf_update_billing, mf_get_billing, and mf_create_billing in the sibling set. An agent can identify the operation without opening the schema.

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?

Gives an explicit precondition: '実行前に必ずユーザーへ確認してください' (always confirm with the user before executing), which tells the agent when/how to invoke it responsibly. It does not name alternatives (e.g., updating vs deleting, or a soft-delete path), so it stops short of full routing guidance.

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