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

With no annotations, the description carries the full burden and does so well: it discloses the matching tolerances (OI change within 3 pp, funding APR within 15 points and same sign, long share within 5 pp, liquidation volume within x2.5), the de-duplication rule (one per day), the archive's start date (2026-09), that output is frequency-based not predictive, and that it is metered with a 100/day free tier. These are exactly the constraints an agent needs before relying on the numbers.

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?

Structure is strong: the guiding question is front-loaded, followed by method, output shape, caveat, and metering. The dense parenthetical list of match thresholds is necessary detail, though the block is long enough that an agent must parse carefully; nothing is outright wasted.

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, and the description compensates by enumerating the returned fields (count, share that went up, median and quartiles, worst and best, base rate, verdict). Combined with the disclosed archive scope and cost model, an agent has enough to decide when to call it and how to read the result.

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 description coverage is 0% for both parameters, so the description must compensate. It partially does: the metering sentence ("free key (100/day), Pro/Bot, or x402") implicitly explains `api_key`, but `coin` is never mentioned even though it selects the market and defaults to BTC. The tolerance thresholds describe the matching logic rather than parameter meaning, so coverage is only partial.

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 a concrete question ("When did the market look like this before, and what did price do next?") and then names the exact mechanism: scanning an hourly archive for hours with similar positioning and returning their 24h/72h price outcomes. That verb+resource+output framing clearly separates it from siblings like get_positioning_regime or get_history, which do not return analog-conditional outcomes.

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?

Usage context is clear: use it when you want historical look-alikes for current positioning and the conditional distribution of forward returns. It also sets an expectation boundary ("NOT a forecast") and flags when results are not trustworthy via `verdict`. It stops short of naming an alternative sibling or stating explicit when-not conditions, so it lands at 4 rather than 5.

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