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

Annotations include readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description reinforces read-only nature, states 'no wallet, no fee, no on-chain action', and adds details like the special meaning of 'short' on spot, and that it is heuristic, not financial advice. This goes beyond 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 front-loaded with the key purpose and is well-structured with paragraphs. It covers purpose, parameters, output, workflow, and disclaimers. While comprehensive, it is slightly long and could be tightened without losing clarity.

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?

Given the complexity of an ensemble ML tool with 7 parameters and no input schema descriptions, the description fully covers the what, how, when, and output details. It includes workflow integration, edge cases (short on spot), and disclaimers. The output schema existence further supports completeness.

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?

With 0% schema description coverage, the description explains most parameters: asset as token mint, timeframe as one of 1m/5m/15m/1h/4h/1d, horizon as forward-return label horizon, buy_threshold/sell_threshold for direction thresholds, lookback_candles for training window. Only caller_id is not explained, which is a minor gap.

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 'ML ensemble directional forecast for a Solana asset (read-only)'. It specifies the tool generates a blended P(up move) score, confidence, direction, per-model contributions, and feature importances. It distinguishes itself from siblings like 'detect_regime' and 'get_signals' by being a directional forecast that complements regime detection.

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 workflow context: 'INTELLIGENCE step -- a directional forecast that complements detect_regime; low confidence -> cut size or stay flat.' It also mentions 'See get_trading_workflow' for more context. However, it does not explicitly state when not to use this tool versus alternatives, leaving some ambiguity.

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