import_statement

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

Beyond the annotations, the description adds critical behavior: step 1 writes nothing, step 2 stores planned rows locally, blocked plans cannot be confirmed, no orders are placed, and previews expire after 15 minutes. These details materially clarify the mutation model and safety constraints.

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 purpose is front-loaded, followed by a tightly structured two-step procedure and key constraints. Every sentence adds operational value with no redundant filler.

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 complex two-step import tool, the description covers the important workflow, write behavior, blocking conditions, and preview expiry, while an output schema exists to describe returns. The remaining gap is the undocumented account parameter, but the overall definition is nearly complete.

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 0%, so the description must carry parameter meaning. It explains file, preview_id, and confirm well, including the two-step interaction, but it does not explain the account parameter or its auto default.

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 verb and resource: importing Toss stock BUY/SELL rows from a private-inbox PDF statement into the local ledger. It clearly distinguishes this import path from sibling read/query tools and states that it never places orders.

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?

It gives explicit two-step usage: first call with file to preview, then call with preview_id and confirm=true to store rows. It also states blocked plans cannot be confirmed, but it does not name any alternative tool or broader when-not-to-use conditions.

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