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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description goes further by disclosing a critical sampling trait — data is recovered from liquidation counterparty fills, is a sample rather than a census, and the payload states its coverage. This provenance detail is meaningful beyond structured annotations.

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 front-loaded with purpose, then gives a caveat, then usage specifics, and closes with provenance. It is compact and every sentence provides useful information, though 'Result carries provenance' slightly overlaps with 'the payload states its coverage.'

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 still enumerates the key return contents: liquidation events, aggregate totals, largest event, and top markets. Combined with schema descriptions for since and minNotional, and annotations for safety, an agent has enough to select and call the tool 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 60%, so the description must compensate. It adds the default limit of 50, clarifies the filterable dimensions (coins, side, minNotional), and frames limit as a cap. It does not add much for 'since', but the schema already documents that parameter sufficiently.

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 opening phrase 'Live liquidation feed on Hyperliquid perps' plus the enumerated outputs (side, size, price, wallet, 1h/4h/24h totals, largest event, top markets) precisely identifies the tool's function and differentiates it from siblings like tape_liquidation_heatmap or tape_live_alerts.

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 concrete invocation guidance: filter by coins, side, or minNotional, and cap with a default limit of 50. It also warns that results are a sample, not a census. However, it does not explicitly state when to choose this tool over its siblings, so the guidance is clear but lacks exclusions.

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