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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the description doesn't need to argue safety. What it adds beyond the annotations is substantive: the exact dataset (Bitvavo daily closes), the currency pair (BTC-EUR), the start date (2019), and the 'so far' as-of-now framing, which signals results shift with the current price. It does not discuss latency, caching, or failure modes, which keeps it off a 5.

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?

A single sentence with no filler, and the core computation leads ahead of the enumerated outputs. The clause stacking ('how often and how long ... so far, the deepest drop and the current drop') is dense on first read but every element maps to a returned figure.

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 carries the return-value burden and does so by enumerating the four reported measures plus the underlying dataset and window. Remaining ambiguity is minor: the unit for 'how long' (days vs. bars) and whether 'top' means the all-time high within the window are left implicit.

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 100% and the sole parameter carries only the terse 'Default 40' in the schema. The description supplies the missing semantics — depth_pct is a threshold measured in percent below the running top, and the output conditions on closes at or beyond that depth. That is real meaning the schema does not convey, earning above the baseline 3.

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 definition names a specific resource and computation: drawdown of BTC-EUR closes versus its top, reported as frequency, duration, deepest drop, and current drop. It also pins the data source and window (Bitvavo daily closes since 2019), so the agent knows exactly what it returns. It falls short of 5 only because it is framed as a question about the output rather than a verb-first statement of the operation.

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?

Usage is implied by the subject matter — reach for this when asked about Bitcoin drawdowns or peak-to-trough history. There is no explicit when-to-use framing, no stated prerequisites, and no mention of any alternative tool for related questions. Since none of the listed siblings overlap in scope, the absence of routing guidance is a smaller gap, but it is still absent.

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