import_csv

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

Without annotations, the description fully discloses the processing pipeline (Stage 0→1+2 classification, confidence routing) and return structure (categorized results, review queue, Markdown report), which is critical for an import tool.

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?

Multiple sentences but each adds value; information is front-loaded and well-organized, though slightly dense.

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?

With no output schema, the description fully explains the return format and processing steps, making it complete for agent decision-making.

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%, so baseline is 3. The description adds meaning by explaining source parameter force vs auto-detect, clarifying generic CSV columns, and emphasizing raw CSV paste.

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 specifies importing CSV from specific sources (弥生会計/freee/MoneyForward or generic) with auto-detection, distinguishing from sibling tools by describing the full classification pipeline and return values.

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?

Provides guidance for auto-detection and a specific tip for 弥生 users, but lacks explicit comparisons to sibling tools like classify_transaction or reconcile_cross_saas.

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