validate_candle_data

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

Describes detection logic, auto-thresholds based on liquidity tier, and adjustable parameters. Without annotations, it could be clearer about read-only nature, but the validation intent is well communicated.

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?

Single paragraph with logical flow: purpose, use case, detection features, auto-tier logic, manual adjustment. It is concise given the number of parameters, though slightly verbose with redundant phrases like '暗号資産のファットテール分布'.

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?

Covers core validation functionality and threshold logic but lacks detail on return format (e.g., whether it returns a score alone or a report with anomaly details). No output schema exists, so description should ideally describe what the agent receives.

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?

Adds meaning beyond schema by explaining auto-threshold behavior for price_sigma and volume_multiplier based on pair tier, and ties pair to liquidity tier. Schema coverage is 71%, and description compensates with contextual value.

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?

Description clearly states the tool validates OHLCV candlestick data quality before analysis/backtesting, detects specific anomalies, and computes a quality score. It uniquely distinguishes from sibling analysis tools by focusing on data reliability.

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?

Explicitly says to use before analysis or backtesting to check data reliability, providing clear context. However, it does not explicitly contrast with sibling tools or state when not to use.

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