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

Annotations already establish readOnly, idempotent and non-destructive behavior, so the description isn't obligated to cover safety. It does add genuinely useful context beyond them: historical coverage depth per pair (BTC from 2013, ETH from 2016) and tier-based limits on intraday and full history. It omits result-size caps, pagination and row limits, which would matter for large intraday pulls.

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 lead sentence is front-loaded with the user question the tool answers, followed by argument guidance and then coverage/limits — a sensible ordering. The re-listing of the interval enum duplicates the schema and could be trimmed, but the rest is dense with no filler.

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?

For a filter-and-fetch tool with no output schema, the description does the right work: it states the return shape (OHLCV bars), the clipping semantics, and the data-availability constraints. The main gap is that start/end date formats and the behavior on oversized ranges are left to inference.

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 only 40%, so the description carries real weight here. It documents `symbol` format (pair, e.g. BTC-USD), enumerates every interval value with a stated default of 1day, and explains that results are clipped to `as_of`. However, `start` and `end` are mentioned with no format, inclusivity, or default behavior, leaving two of five parameters still under-specified.

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 verb and resource — returns OHLCV bars for 512 crypto pairs — and frames the question it answers ('what did BTC do?'), so an agent immediately knows the domain. The crypto scope implicitly separates it from get_bars, get_fx and get_futures, but no sibling is named, so the differentiation is inferred rather than stated.

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?

It gives clear conditions for use: supply a pair symbol, optionally interval/start/end, and expect bars clipped to as_of. It also flags the plan-dependent gating (free keys = daily bars for 12 months only), which tells the agent when a call may return limited data. It stops short of explicit exclusions or naming the tool to use for non-crypto assets.

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