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

With no annotations provided, the description carries the full burden — and it delivers exceptional detail. It discloses look-ahead-free construction, which inputs are revision-safe (price, calendar, chain) vs. third-party-revisable (fear_greed, btc_dominance), the walk-forward vs. reconstructed data split (since 2026-04-17), and the critical warm-up caveat that early rows carry raw scores under the same field name. This is far beyond what annotations would typically supply.

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 information density is high and every sentence earns its place — the conceptual question is front-loaded, and the warm-up and data-provenance caveats are genuinely necessary for correct interpretation. However, it is one dense wall of text; paragraph breaks would materially improve scannability for an agent parsing the description. Slightly over-long but never wasteful.

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?

Despite having no output schema, the description fully specifies the return shape (time series, one row per day, fields adj_score and z_adj_score, ascending by date) and pre-empts the two biggest misinterpretation risks: the z-score warm-up semantics and the reconstructed-vs-observed data split. For a single-parameter timeseries tool, nothing an agent needs to call it correctly is missing.

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 sole 'days' parameter is already documented as 'Number of days back from today (auto-clamped by tier)'. The description adds the concrete tier values (30/365/3650) and reinforces the clamping behavior, which is marginal value. Baseline 3 is correct since the schema does most of the work and the description adds only light amplification.

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 ('How has the cycle score moved over time?') and names the exact resource (BTC-Cycle TIME SERIES with adj_score and z_adj_score, one row per day, ascending by date). It explicitly differentiates from the sibling tools by naming arena_get_cycle for the current single reading and arena_get_historical_analog for historical analog comparisons, so an agent can distinguish it without opening other schemas.

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?

Routing guidance is explicit and actionable: 'For the current cycle reading alone call arena_get_cycle; for what similar historical readings were followed by, call arena_get_historical_analog.' It also states the tier-based range cap (Free 30d / Pro 365d / Power unlimited), which sets expectations for what the days parameter will return. This leaves nothing about when-to-use to inference.

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