Modify an open order

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description adds substantially more: the imperative 'confirm the new terms with the user first,' the US-stock 400 us-modify-quantity-not-supported rejection, and the hard rejection of orders ₩3,000,000,000 or more. Error codes (409 already-filled/already-canceled/already-modified/already-processing, 422 modify-restricted, 404 order-not-found) and the return shape { accountSeq, orderId, operation: 'modified' } give the agent concrete recovery paths.

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?

Front-loaded with the action and the real-order safety warning, followed by scannable Args/Returns/Errors sections. The length is justified for a real-money destructive tool, though the Args section partially duplicates the already-detailed schema descriptions. Every sentence earns its place overall.

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 mutation tool with 7 parameters and real-world consequences, the description covers preconditions, per-market behavior, high-value confirmation flow, return payload, and all documented error paths. The output schema exists, so return values need no further detail. Nothing an agent needs to call it correctly and safely is missing.

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%, so the baseline is 3. The Args section nevertheless adds actionable meaning beyond the schema: the specific 400 error for US quantity, the ₩100M/₩3B thresholds governing confirm_high_value_order, and account_seq auto-resolution for single-account credentials — details that change call construction, not just labeling. It does not fully compensate for everything, but it adds genuine value above an already-rich schema.

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?

Opens with a specific verb+resource statement — "Change the price (and, for Korean stocks, the quantity) of a working order" — that precisely names the action and target. The safety-critical framing "This alters a REAL order" makes it unmistakable that this is a mutating tool, clearly distinct from sibling create/cancel/read tools. The title 'Modify an open order' aligns perfectly with the description.

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?

States the precondition explicitly: the order 'Must still be working; get it from tossinvest_list_orders with status='OPEN'.' This tells the agent how to source a valid order_id and when this tool applies. It does not explicitly name alternatives or exclusions (e.g., 'use tossinvest_cancel_order to remove an order instead'), so it stops short of a 5, but the context is clear.

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