create_invoice

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

Annotations already cover idempotency and non-destructiveness. The description adds a key behavioral trait beyond annotations: the invoice is created but not sent (送付は行わない), preventing misuse where the agent expects sending. It does not disclose return details, but the output schema likely covers that.

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 a single, front-loaded sentence with two essential pieces of information: the primary action (create invoice) and a critical limitation (does not send). Every word contributes value, making it appropriately concise.

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?

Despite having 16 parameters and multiple required fields, the description is minimal and does not explain the invoice-creation workflow, required data, or any special rules. It only clarifies the non-sending aspect. The low schema description coverage and absence of parameter guidance make this incomplete for a complex 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 31%, and the description provides no parameter-level explanations. Field names like operation_key, document_template, client_contact_mid, and tax_type are left without clarification, so the agent must infer meaning from names alone. With low coverage, the description fails to compensate.

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 clearly states the verb and resource: 'Create an invoice in MakeLeaps' (請求書を作成する). It also adds a scope limitation 'does not send' (送付は行わない), which distinguishes this tool from sending-related actions and sibling tools like create_quote.

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 establishes clear context (creating an invoice) and explicitly states a when-not: 'does not send it' (送付は行わない), implying this tool should not be used when the goal is to send an invoice. However, it does not explicitly name alternatives or specify when to choose this over siblings.

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