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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly lists the sequence: market reduce-only order, cancellation of exchange SL/TP orders, and recording of realized PnL. It also state the return payload. This goes well beyond the schema and makes the side effects clear. It does not mention failure modes or partial-execution scenarios, but the core behaviors are adequately documented.

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 two sentences: the first states the action and its sub-steps, the second lists the parameters and return. It is front-loaded with the main purpose and has zero filler. Every clause contributes to understanding the tool's function, making it appropriately concise and well structured.

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 tool with only two parameters and no output schema or annotations, the description covers the action, the methodological steps, the return value, and provides parameter examples. It is notably incomplete in documenting error handling or prerequisite checks (e.g., whether an open position must exist). However, these are relatively minor given the simple parameter surface, and the description provides sufficient information to invoke the tool correctly in most agent scenarios.

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 provides no descriptions for the two parameters (exchange and symbol), and coverage is 0%. The description compensates by giving an example for symbol ('BTC_USDT') and implicitly limiting exchange to the platforms mentioned earlier (binance/bingx/bybit). It does not enumerate exact allowed exchange values or fully specify symbol formatting, but it provides enough semantic context for an agent to form correct inputs. The description adds moderate value beyond the 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?

The description clearly states the specific action: closing an open position from the user_positions registry. It details the mechanism (market reduce-only), secondary operations (cancel exchange SL/TP, record realized PnL), and the return value (fill price and PnL). This distinguishes it from sibling tools like place_order (generic order placement) and close_hedged_position (which targets hedged positions specifically).

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 clearly indicates when to use this tool: when closing an existing position in the user_positions registry. It implies this is the preferred tool for closing positions (as opposed to opening or hedging), and the reduce-only caveat further clarifies scope. However, it does not explicitly name alternative tools or state 'do not use this for opening positions', leaving some OUSAGE inference to the agent. The context is strong enough for correct routing.

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