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

With annotation readOnlyHint=true and openWorldHint=true, the safety/read-only profile is already known. The description adds useful behavioral context—this is a momentary snapshot and should not be overinterpreted—but does not disclose deeper traits such as the exact calculation method or whether the bias thresholds are configurable. Acceptable but not rich.

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?

Three short, information-dense sentences. Each sentence adds value: core output, sibling comparison, and a critical caveat. There is no fluff or repetition.

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 one-parameter read-only metric tool without an output schema, the description is complete enough for an AI agent to choose and call the tool correctly. It explains what the tool returns (percentages, depths, bias labels), distinguishes it from the raw order book snapshot sibling, and provides a caveat about interpretation.

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 only parameter, 'symbol', is fully described in the input schema with pattern, length, and example. Schema description coverage is 100%, so the description does not need compensating parameter details. Baseline of 3 is appropriate.

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 defines the tool's output: cumulative Bid vs Ask imbalance percentages at three depths (5, 10, 20) plus bias labels, and explicitly distinguishes it from binance_get_order_book_depth. This makes the tool's purpose and differentiation from sibling tools immediately clear.

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 clear usage context: it contrasts this tool with the raw-snapshot sibling and warns that the value is a momentary snapshot that should not be overinterpreted. It stops short of explicitly saying 'use this when you want a bias label' or naming additional alternatives, so it is clear but not overly prescriptive.

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