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

With readOnlyHint=true, the safety profile is already supplied by annotations; the description adds valuable behavioral context by stating the tool does not fetch its own data, walks bids downward for LONG and asks upward for SHORT, and reports HIGH_DATA_INCOMPLETE when validation fails. This tells an agent exactly what will happen at runtime.

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?

Two sentences front-load the purpose, then cover direction behavior, data-injection mode, and sibling differentiation without padding. Every clause serves a distinct decision an agent needs to make.

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 an 8-parameter tool with no output schema, the description is almost sufficient: it names return categories, explains direction-specific behavior, and states caller-injected data. It could add a little more detail on why OI validation matters or how thresholds are applied, but the essential calling context is present.

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 only 38%, so the narrative must carry meaning. The description maps the main parameters to the computation: bids/asks for depth, currentPrice/stopLossPrice for the SL path, openInterest for validation, and positionSide for direction. slippageThresholdUsd is the only parameter left to rely on the schema, which already documents it.

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 opens with a specific verb and object: checking whether order book depth can absorb a stop-loss without severe slippage, and mentions the three concrete output labels (LOW/HIGH_SLIPPAGE_RISK/HIGH_DATA_INCOMPLETE). It also explicitly separates itself from analyze_futures_grid_risk, so an agent can distinguish it from that sibling without opening the schema.

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 states the tool is a simple liquidity check, says it supports both LONG and SHORT, and explicitly warns it is NOT a replacement for analyze_futures_grid_risk, which orients the agent toward the right alternative. It stops short of defining precise conditions for choosing this tool over estimate_slippage or analyze_futures_grid_risk, but the core usage context is clear.

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