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

Even though readOnlyHint already conveys safety, the description adds substantial behavior: output shape (a single positioning bias in [-1,1]), per-component reasoning, per-line data freshness, and a coverage grade that explicitly warns thin coverage should not be read as full coverage. This goes beyond the annotations and gives the agent an honest model of how to interpret results.

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 and contains dense, valuable content in a single paragraph. It is heavier than needed and takes one long run-on sentence, but every sentence earns its place; no filler or unnecessary restatement.

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 walks the agent through input, composition, output type, interpretation caveats, coverage grading, and an alternative route. It also says it mirrors a REST endpoint and frames itself as conditioning context, making it effectively complete for an agent to select and invoke the tool.

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 schema only declares 'coin' with a default of 'BTC' and no description, and the prose says 'for one coin' but no accepted value format or example is provided. Since schema description coverage is 0%, the description partially compensates by making the single-coin scope clear, but it leaves the actual coin identifier semantics ambiguous.

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 opens with a clear verb + resource: it provides a positioning thesis for a single coin and states it decides 'who is crowded and which way.' It enumerates distinct inputs and output and even calls out its alternative, so an agent can distinguish it from every sibling immediately.

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 gives an explicit directive: 'Use INSTEAD of manually combining get_liquidation_map + get_options + funding.' This makes the primary use case clear, but it doesn't state exclusion cases or say when raw underlying data is still needed, so it is clear but not fully complete guidance.

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