Order-flow toxicity (VPIN) for BTC, ETH, SOL perps

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

The description defines the VPIN scale (0=balanced, 1=fully one-sided) and adds interpretive context ('Elevated readings historically precede volatility'), which goes beyond the readOnlyHint annotation. It honestly caveats that VPIN says nothing about direction, improving the agent's understanding of the tool's limitations. The annotation and description are consistent; no contradiction.

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 three sentences, each with a distinct purpose: trigger condition, output description, and interpretive caveat. It is front-loaded with a clear 'Call this when' opening and contains no filler or redundant information.

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?

For a zero-parameter read-only tool without an output schema, the description is complete enough: it names all key return values, defines the metric's meaning, and provides a historical interpretation. It stops short of exact formatting, but that's acceptable given the simple output structure and the read-only annotation.

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 tool has zero parameters, so the baseline for parameter semantics is high. The description doesn't need to explain input syntax but instead clarifies the output fields (VPIN, percentile, danger threshold, 24h average), adding meaningful value beyond the empty schema.

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 clearly states the tool's purpose with specific trigger phrases ('when the user asks whether informed or toxic order flow is building, about VPIN, or whether market makers are under pressure') and names the exact assets (BTC, ETH, SOL perps). It distinguishes itself from sibling tools by focusing on toxicity/VPIN, a unique metric not covered by the listed 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?

The description provides explicit when-to-use guidance with concrete user intents ('when the user asks...'). It also gives a when-not signal by stating 'VPIN says nothing about direction,' which helps avoid misuse. While it doesn't name alternative sibling tools, its scope is explicit and the sibling list makes alternatives evident.

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