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

With no annotations, the description carries the full burden. It discloses that the data is measured (not modeled), covers only large accounts, and lists the temporal range options. It also gives a leverage recommendation. This is transparent about scope and range, though it doesn't discuss rate limits or authentication, which are typically not critical for a read-only data tool.

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 packs substantial information into one sentence: source (Hyperliquid), type (MEASURED), coverage, contents (bins, notional, curves, positions), and range options. It is efficient and front-loads the key qualifier 'MEASURED (not modeled)'. Slight run-on but overall well-structured.

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?

Given no output schema, the description outlines the expected output: binned positions, notional per bin, cumulative curves, and largest positions. It also covers temporal range and coverage limitation. This is adequate for an agent to understand what it will receive, though it doesn't detail response format or pagination. For a tool of moderate complexity, this is fairly complete.

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. It explicitly lists valid values for 'range' (12h | 1d | 3d | 7d | max), which is helpful. However, it does not describe the 'symbol' parameter beyond implying it's a trading pair. The description adds value for range but leaves symbol semantics implied, not fully compensating for the lack of schema docs.

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 states a specific resource (Hyperliquid liquidation map) with distinctive qualifiers 'MEASURED (not modeled)' and 'Partial coverage: large accounts only'. This differentiates it from siblings like get_liquidation_map or get_liquidation_heatmap, and clearly conveys the data content: bins, notional per bin, cumulative curves, and largest positions.

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?

It provides context on when to use it: when measured rather than modeled data is needed, and notes the coverage limitation ('large accounts only'). It also gives a usage recommendation ('large accounts run low leverage'). However, it does not explicitly name alternative tools or state when not to use it, so explicit exclusions are missing.

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