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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint, destructiveHint=false), lowering the bar. The description adds one genuinely behavioral detail – data is scoped to the top liquidity pool rather than an aggregate – which is non-obvious and useful. But it omits other operationally relevant traits like history depth, data freshness, or how pool selection changes over time. No contradiction with 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?

Two short, information-dense sentences with zero filler: the first fixes the output and scope, the second enumerates supported timeframes. The core function is front-loaded before any secondary detail, and every clause earns its place.

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 read-only tool with no output schema and 3 well-constrained params, the description covers the essentials: what is returned (OHLCV), the supported timeframes, and the pool-scoping caveat. However, with no output schema present, the description carries the burden of explaining the return shape (candle ordering, timestamp format, field structure) and any history limits, which are absent. Annotations compensate for the safety side, keeping this at a minimum-viable 3.

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 only 33% (only `timeframe` is documented), so the description needed to compensate for `chain` and `address`. Instead, it merely restates the timeframe enum values already present in the schema and adds no meaning for `chain` (e.g., network context) or `address` (e.g., token address format). The 'top pool by liquidity' clause is tool-level context, not parameter semantics.

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 precisely identifies the output ('OHLCV candles') and the resource ('a token'), and sharpens scope with 'top pool by liquidity', making the function unambiguous. The explicit verb comes only from the title/name ('Get'), not the description itself, so it stops short of a 5.

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?

Usage is implied by the resource type – an agent wanting price chart data would select this tool, and the sibling set (swap building, quotes, instant shifts, onramps) is functionally distinct. However, the description states no explicit when-to-use or when-not-to-use conditions, and names no alternative, leaving routing largely to inference.

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