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

Annotations mark this as destructive (destructiveHint: true) and non-read-only (readOnlyHint: false). The description adds that position_amount is 'base units of target_token to liquidate on trigger,' clarifying the execution side effect, and refers to a 'monitor' which implies ongoing auto-liquidation. It does not mention that creating this monitor may override or cancel existing ones, nor does it warn that trading will occur. Given the annotation already flags destructiveness, the description adds some context but not comprehensive behavioral detail.

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 concise, front-loaded with the primary purpose, then dives into the most critical parameter (position_amount) and a key constraint (at least one trigger). It groups related parameters (direction settings) and points to another tool for details, avoiding repetition. The structure is logical and compact, though it skips over many other parameters.

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?

Given the tool has 15 parameters, 3 required, and no schema descriptions, the description falls short. It does not explain the meaning or interaction of most parameters, nor does it mention what happens upon trigger (e.g., market order execution, fees, partial fills). It also does not clarify the role of wallet_address and target_token beyond implying a held position. While an output schema exists, the description does not enrich understanding of the tool's behavior or edge cases, making it incomplete for reliable invocation.

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 explain parameters itself. It covers only position_amount, stop_loss_pct, take_profit_pct, trailing config, and direction_mode/allow_short/regime_override via a reference to strategy_dca_create. It does not explain risk, entry_price, slippage_bps, source_token, target_token, wallet_address, interval_seconds, trailing_distance_pct, or the exact relationship between trailing (boolean) and trailing_distance_pct. Many parameters remain undefined, leaving the agent to infer their meaning. This is insufficient for a 15-parameter tool.

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: 'Create a stop-loss / take-profit / trailing-stop monitor on a held position.' This specifies the verb (create), resource (monitor), and its three variants, distinguishing it from other strategy creation siblings like strategy_dca_create and strategy_arb_create. It also hints at the scope (on a held position) without ambiguity.

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 gives a key usage rule: 'At least one of stop_loss_pct / take_profit_pct / a trailing config should be set.' It also points to strategy_dca_create for direction-related parameters, indicating where to look for additional options. However, it does not explicitly state when to choose this tool over, say, strategy_protect_create or strategy_hedge_create, nor when not to use it. The guidance is useful but not fully prescriptive.

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