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

The annotations (readOnlyHint=true, openWorldHint=true) are consistent with the description (a read-only data fetch). The description adds valuable context: the default summary mode returns derived metrics and at most 10 points to save tokens, and the 'detail: full' option provides raw levels. It also warns about potential output size. The openWorldHint is not elaborated, but the description covers the main behavioral aspects.

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 description is moderately long but front-loaded with the core purpose and endpoint. It uses an em-dash to break up the content, which is a stylistic choice. The use cases and differentiation appear early, and the default/detail explanation is efficient. Slightly verbose but no redundant fluff.

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 simple read-only tool with full schema documentation and no output schema, the description covers the essential distinctions from siblings and the key behavior modes. There is no mention of pagination or exact output structure, but the summary/full detail is explained and references a docs file. The tool is not complex, and the description is adequate for correct invocation.

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 parameters are already fully documented. The description adds context for the 'detail' parameter (summary vs full) and explains the token-saving benefit, which goes beyond the schema's description. The 'symbol' parameter description mentions it is sent as 'pair' to Binance, adding useful API mapping. However, since the schema already covers most semantics, a baseline of 3 is appropriate.

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 explicitly states the tool fetches historical basis data from Binance's official endpoint, distinguishing it from the sibling binance_get_basis_history. It clearly specifies the resource (futures data basis endpoint), the measured quantity (futures price vs index price), and the period intervals. The distinction from the sibling is crisp: this tool is the source of truth for historical premium/discount, while the sibling uses a snapshot D1 cron with a fixed watchlist.

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 description names the sibling tool explicitly and explains the key difference (snapshot D1 cron vs official endpoint), making it clear when to choose one over the other. It also lists specific use cases: detecting extreme premium, mean-reversion basis, and confirming funding lag. No exclusionary conditions are mentioned, but the use cases and differentiation are strong.

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