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

Adds substantial behavior beyond the read-only/idempotent annotations: each call counts as one API call, the plan determines whether history is included and how far back, rangeClamped signals a shortened window, historyLimit names the limiting plan, signed rows require includeSignedRows=true, and an empty page means no recorded history rather than a zero price. That is exactly the operational context an agent cannot get from annotations.

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?

Front-loaded with what is read, then dataset semantics, plan behavior, cost, pagination and the empty-page caveat in order of importance. Dense and mostly waste-free, though the dataset explanation partially restates the enum description in the schema.

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 the tool's complexity (9 params, plan-driven clamping, signed vs unsigned data, pagination) the description covers every decision the agent must make. With an output schema present it needn't describe return shapes, and it still supplies the interpretive cues for rangeClamped, historyLimit and empty pages.

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 schema already documents all 9 parameters and the baseline is 3. The description adds value the schema lacks: the verified/reconstructed provenance distinction, the requirement that signed rows be verified with verify_print, and the cursor-reuse rule tying cursor to the same symbol/dataset/interval.

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?

Opens with a specific verb+resource ('Read price history for one crypto symbol from /api/index/v1/history') and enumerates the candle fields and intervals it returns. It implicitly distinguishes itself from lighter siblings like get_index_price and get_index_batch by scoping to candle history with metrics and pagination.

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?

Gives explicit conditions for choosing dataset=verified vs reconstructed (reconstructed is 1h/1d only and unsigned at the time), plus concrete pagination instructions ('pass pagination.nextCursor as cursor with the same symbol, dataset and interval'). It does not explicitly route the agent away from sibling tools such as get_index_price or get_index_batch, so it falls short of full alternative coverage.

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