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

Annotations already mark it read-only, open-world, idempotent, and non-destructive. The description adds crucial behavioral nuance beyond those flags: that data is 'measured from the venue aggressor tag, not inferred from bar direction,' and that the tool 'reports coveredMinutes, not the minutes asked for.' Both details meaningfully affect how an agent interprets results and cannot be gleaned from the schema or annotations.

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 dense but every clause earns its place: it opens with the output content, states the methodological basis, provides a concrete when-to-use signal, explains the two calling modes, and closes with a key output caveat. It is front-loaded with the most decision-relevant information and contains no filler.

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 tool with 10 parameters, no output schema, and subtle temporal behavior, the description covers all essential context: what is returned, how it is measured, how to request single vs. multi-candle windows, and a behavioral quirk (coveredMinutes). An agent can invoke the tool correctly and interpret its results without further discovery.

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 90% and already explains most parameters, including the role of candleTime and bucketSize. The description adds a useful clarification by tying candleTime and minutes into a single mental model (exact bar vs. trailing window) and explicitly warns about the coveredMinutes mismatch. This goes beyond the schema's per-field documentation, though most parameter semantics remain in the 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 opens with a precise inventory of what the tool computes ('buy and sell volume separated by who crossed the spread, delta, the footprint by price level, the point of control, and absorption or stacked imbalance') and explicitly contrasts it with candles ('use it when the question is who is being aggressive, which candles cannot answer'). This distinguishes it from the many chart/candle siblings and gives an agent an unambiguous picture of the tool's unique role.

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 states exactly when to reach for this tool ('use it when the question is who is being aggressive'), and it differentiates from alternative candle-based analysis. It also provides explicit invocation guidance for the two modes ('for one candle pass candleTime... otherwise it reads the last minutes') and warns about the coveredMinutes discrepancy. This is actionable, not generic.

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