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

Annotations cover safety (readOnlyHint, openWorldHint), but the description adds real behavioral context beyond them: the Builder/Scale/PRO tier requirement, the fact that a subscription check gates the download address, and the two-step flow where the signature/address is returned here and the file itself is fetched with the same Bearer token. It omits rate limits or format details of the signature, hence not a 5.

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?

Two dense sentences, front-loaded with the pack contents before mode and auth details. The embedded example URL consumes space but is functional, and nothing is redundant given the schema carries no descriptions.

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 and a single bare enum parameter, the description covers the essentials: what the packs contain, the list-versus-download branching, the tier prerequisite, and the shape of the return (download address plus signature). Only minor gaps remain around response format specifics.

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%, so the description must carry the burden, and it does: it maps the pack values to their markets (BTC/ETH/SOL/XRP/WLFI → *-core), gives a concrete example (btc-core), and explains the behavior when the parameter is omitted. The enum values themselves are only partially self-explanatory, which keeps it from a 5.

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?

States a specific resource (historical data packs per market) with concrete contents: 730 daily candles, 1000 hourly candles, daily open interest across 13 exchanges, and daily spot ETF flows as signed JSON or CSV. This clearly distinguishes it from siblings like get_price_history, get_open_interest, and get_etf_flows, which expose those datasets individually rather than as bundled packs.

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?

The two operating modes are explained (no pack = list packs; with a pack = retrieve download address), which is implicit usage guidance. However, it never states when to prefer a data pack over the sibling point-read tools, and the tier-gating condition is mentioned only in passing rather than framed as a prerequisite the agent must check.

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