ecount_create_invoice

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

No annotations are provided, so the description carries the full burden. It goes beyond a simple create statement by disclosing the rate limit (10초/1회), the response structure (success, failed, slipNos, details), and the conditional account selection behavior. This is substantive operational context, though it does not mention session prerequisites or idempotency.

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 dense paragraph with structured bracket sections for rate limit and response. Every sentence adds value—tax codes, account selection, input amounts, and response details—with no filler. Slightly long but appropriate for the tool's complexity.

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 create-invoice tool with no output schema, the description covers key operational aspects: rate limit, response format, tax type codes, and account code rules. It does not mention batch size limits (though schema has maxItems 300) or session/auth requirements, but these are partially covered by sibling connection tools and schema.

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?

The schema already has 100% parameter description coverage, but the description adds meaningful relational semantics: it explicitly links TAX_GUBUN to whether CR_CODE (매출) or DR_CODE (매입) should be used, and gives example account codes. This clarifies usage beyond the individual schema descriptions.

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 that this tool registers accounting vouchers (tax invoices) in ECOUNT with automatic journal posting ('매출·매입전표 II 자동분개'). It specifies the resource (회계 전표) and the action (등록), and the tax/accounting focus distinguishes it from sibling tools like product or customer creation.

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 internal guidance on when to use CR_CODE vs DR_CODE based on TAX_GUBUN, but does not explicitly state when to use this tool versus alternatives like ecount_create_sale or ecount_create_purchase. The usage context is implied by the term '회계 전표' but no exclusions or alternative recommendations are given.

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