Recorded series: bars or points of one metric for one perpetual (price, OI, funding, CVD, liquidations, long/short, RSI and more)

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

Annotations only declare readOnlyHint and openWorldHint, but the description adds substantial behavior: the exact response shape (points as [t, v], OHLCV for price, plus unit, kind, source, source_kind, bars served, member depth and provenance), depth/authorization behavior (public depth serves fewer bars and no 5m bars; Builder key and above get member depth), and where bar limits live. This is genuinely useful context beyond the structured fields.

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 trigger is front-loaded and the prose is information-dense with little filler, but it is long and partly redundant, listing the metric set once in prose and again in the 'metric is one of' clause. It is appropriately sized for a broad time-series endpoint, though not maximally tight.

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 explanation and does so (point/tuple format, unit/kind/source fields, bar count, provenance), plus depth limits and the metric list. For a 7-parameter, high-complexity endpoint, an agent has everything needed to call it correctly.

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%, so the baseline is 3, but the description adds real semantics: the full metric key list, venue support notes, and the rule 'Pass from and to (ISO) for a window, or limit for the newest bars', which explains how parameters interact rather than restating them. It adds value over the schema without fully documenting every parameter's edge behavior.

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?

Opens with a precise verb+resource+scope: the history of one recorded metric for one perpetual as a time series, and enumerates the metric space (price, volume, CVD, OI, funding, liquidations, RSI, ETF flows, whale net flow, etc.). An agent can distinguish it from single-metric siblings like get_open_interest or get_etf_flows because it is framed as the general time-series endpoint.

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?

Gives a clear when-to-use trigger: history for one metric/one perpetual, for charting, backtesting or 'what did X do over the last N days'. It also implies usage via the metric list and the from/to vs limit guidance. It does not explicitly name when NOT to use it or route to specific sibling tools (e.g., prefer get_liquidations for a cascade view), so it stops short of full alternative routing.

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