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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: null sections mean unavailable or insufficient observations, and the `minimums` field must be consulted to interpret them, plus the 'legacy' framing signals this data may be superseded. It does not discuss cost, latency, or whether the record is cached.

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 sentences, front-loaded with the identity of the resource and followed by the disambiguation and the null-handling caveat. Every sentence carries distinct information, though the metric jargon ('Brier/log transforms', 'price-bin frequencies') is dense and could have been one clause shorter without loss.

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?

An output schema exists, so return values need not be enumerated, and the description correctly focuses on the interpretive caveat (nulls + `minimums`) that the output schema alone may not make obvious. For a read-only, single-parameter diagnostic endpoint this is close to sufficient; only the absence of a positive use case and of any statement about which wallet addresses are valid leaves a gap.

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?

There is a single required parameter (`address`) with 100% schema description coverage and a defined EVM address pattern, so the schema fully carries parameter semantics. The description adds no meaning about the address — e.g., whether it must be a trader, a linked wallet, or whether unlinked addresses return nulls. Baseline 3 applies when the schema does the work.

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 names a concrete resource and content set: Brier/log transforms, price-bin frequencies, and streak/best-call fields computed from execution/post-fill prices. It also draws explicit boundaries against related concepts ('not the trader's stated probabilities', 'separate from the fixed-lock Arena record', 'no championship rank'), so an agent can tell it apart from the forecaster/arena scoring surfaces. It stops short of naming a specific sibling tool, which keeps it from a 5.

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 tells the agent what this is NOT (stated probabilities, forecast accuracy, Arena record, championship rank), which is useful negative routing, and instructs it to read `minimums` when sections are null. However, it never states a positive trigger such as 'use this when you need legacy trade-derived calibration metrics for a wallet' or names the alternative tool to call instead. Usage is implied rather than prescribed.

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