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

With no annotations, the description carries the full burden and does well: it discloses the data is exchange-measured rather than modeled, and explicitly warns of partial coverage (large accounts only). It does not mention permissions, rate limits, or pagination, so it falls short of full disclosure.

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 core identity and the model/measurement distinction, then the coverage caveat, then range values. Dense but every clause carries information; minor awkwardness in fragment-style phrasing.

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, so the description usefully enumerates the returned constructs (long/short notional per bin, cumulative curves, largest positions) and the coverage limitation. Missing only the meaning of 'symbol' and any guidance on the retentive range default beyond the schema default.

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 0%, so the description must compensate, and it largely does: it enumerates the valid 'range' values (12h | 1d | 3d | 7d | max) and adds a selection hint. 'symbol' is left unexplained, so compensation is incomplete for a 2-param 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?

States a specific verb+resource ('Liquidation map for Hyperliquid') and immediately scopes it as measured data ('not a model'), which distinguishes it from the sibling get_liquidation_map. It further specifies the exact content (leveraged positions of the 10,000 largest accounts binned by liquidation price, long/short notional, cumulative curves).

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?

Provides useful context ('Partial coverage: large accounts only', 'recommended: large accounts run low leverage') and lists valid ranges, but never states when to pick this over nearby siblings such as get_liquidation_heatmap, get_liquidations, or get_liquidation_cascades. Usage is implied rather than routed.

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