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

Annotations cover the safety profile (readOnly, non-destructive, openWorld, non-idempotent), so the bar is lower, yet the description still adds real behavioral context: hash commitment, append-only/never-revised immutability, and the auth model (Coil Live subscription, 7-day trial, or x402 per-call wallet). It also discloses the failure mode — a PaymentRequired object and no data — which an agent needs before calling.

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?

Purpose and immutability are front-loaded, then the index behavior, then auth/payment — a sensible order with little filler. The subscription/payment paragraph is dense, and the phrase 'this read returns live data' inside an archive tool is confusing rather than informative, costing a point.

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 burden of explaining returns, and it does so for both special cases (archive index without `date`, PaymentRequired without entitlement). Auth and payment prerequisites are fully covered. It does not describe the shape of a successful score payload, but that gap is minor for a single-parameter read.

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?

There is one optional parameter and schema description coverage is 100%, so the schema already documents the YYYY-MM-DD format. The description adds the meaningful behavioral nuance that omitting `date` switches to an archive-index listing, but otherwise repeats what the schema states — baseline 3 for high coverage.

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 first clause states a specific verb and resource with a distinctive scope: the point-in-time archive of scores published on an archived date, sha256-committed and append-only. That distinguishes it from the many live/board siblings without naming them. The later 'this read returns live data' line, dropped into a subscription discussion, muddies an otherwise crisp purpose.

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?

'Backtest-grade provenance' implies the when-to-use case (historical reproduction), and the date-omission behavior is spelled out. However, no sibling is named as an alternative (e.g. get_day_board or get_day_board_live) and there is no explicit when-not-to-use guidance, so routing is left partly to inference.

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