Auto-detected liquidation cascades (forensic case file)

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=true), and the description adds non-obvious context: the totals are 'an honestly-labeled lower bound from a real liquidation tape,' which tells the agent the figures are flooring estimates derived from observed data. It stops short of disclosing lookback depth, incident count, or aggregation methodology.

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?

Three tight sentences: trigger first, return payload second, data-quality caveat last. No filler, and the most decision-relevant information (when to call) is front-loaded.

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?

With no output schema, the description carries the return-shape burden and does so by enumerating the incident fields. However, a zero-parameter tool gives the agent no control over scope, and the description never states the lookback window or how many incidents come back — relevant since the user's 'recent crash' may not match the detector's window.

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 tool takes zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description usefully fills the vacated space by describing what the parameterless call returns.

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?

Names a specific deliverable ('auto-detected cascade incidents') and enumerates the returned fields (timing, notional flushed, long/short split, leading coins, BTC move), which distinguishes it from the raw-tape sibling get_liquidations. It does not explicitly name siblings, and the phrase 'who got liquidated' partially overlaps with get_liquidation_leaderboard, so the differentiation is strong but not airtight.

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?

Opens with an explicit invocation trigger: 'Call this when the user asks what caused a recent crash or flush, about liquidation cascades, or who got liquidated.' That gives clear context for selection, though it states no exclusions or conditions pointing to alternative tools.

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