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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states output compositions for each metric (e.g., 'oi returns open-interest candles (USD)'), and reveals that timestamps are UTC ISO 8601 and results are the newest N points. This adds significant transparency about return format and ordering, though it omits rate limits or error behavior.

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 three sentences: purpose, per-metric returns, and timestamp/order info. Every sentence provides essential information with no fluff. The density in the metric list is acceptable given the number of metrics, and the structure is front-loaded with the core purpose.

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?

There is no output schema, so the description must explain return values, which it does thoroughly for each metric. It also clarifies ordering and timestamp format. However, it does not describe the exact JSON field names (e.g., 'open', 'high', 'low') or clarify whether prices are aggregated across exchanges, which leaves some ambiguity in a no-schema context.

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?

The schema covers symbol, tf, and limit with descriptions, but metric has no schema description. The description compensates by explaining exactly what each metric enum value returns (e.g., 'funding returns OI-weighted funding-rate candles (% per interval)'). This adds meaningful semantic detail beyond the raw enum list, though tf and limit rely on 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 'Historical time series for one coin' and then enumerates exactly what each metric returns (OHLC, OI, funding, long/short, liquidation, volume). This is a specific verb + resource + scope, and the detailed metric list clearly distinguishes it from sibling tools like get_funding_rates (which likely handles current rates) and get_market_overview.

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 gives clear context for when to use the tool: any time historical series for these specific metrics are needed for a single coin. It does not explicitly mention alternatives or exclusions, but the per-metric breakdown implicitly tells the agent which metric to choose. A 5 would require explicit 'instead of X' guidance.

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