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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is semantics, and it delivers: the baseline is always the trailing 7 days regardless of the display window, and market_wide has a non-obvious definition (three or more unrelated coins in the same minute). It stops short of stating response size, ordering, or whether the 7-day baseline limits how far back hours can go.

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 definition, then routing, then return fields, then a non-obvious note — a good information order. The enumeration of per-event fields ('coin, which side broke, start, how long it ran, total and peak-minute USD...') is dense but every item tells the agent something it could not otherwise know in the absence of an output schema.

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?

No output schema exists, so the description compensates by enumerating the per-event fields and defining market_wide. Combined with annotations covering safety and a fully documented 2-param schema, an agent has everything needed to select and call this correctly.

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 coverage is 100%, so baseline is 3, and the description earns above it by disambiguating hours as a 'display window' whose comparison baseline stays fixed at 7 days — a distinction the schema's 'Look-back window in hours' does not convey and which materially changes interpretation. The limit parameter is not mentioned in the description at all.

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?

States a specific resource and shape: 'Liquidation CASCADES as discrete events: bursts of liquidations detected against each coin's own 7-day normal minute.' The term 'discrete events' plus the normalized-baseline definition makes it immediately distinguishable from summary, raw-order and map siblings.

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?

Gives an explicit use case in the user's own words ('when did forced selling snowball and what did price do') and then names three exclusion families by tool name: totals (get_liquidations_summary), raw orders (get_liquidations), and open positions at risk (*_liquidation_map). Nothing about routing is left to inference.

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