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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-structural context: the verdict taxonomy (ok/caution/avoid, and 'unknown when data is missing') and the per-call cost (0.030 USDC, included in subscriptions). It stops short of describing latency or failure/error behavior for unsupported pools.

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?

Structurally sound and front-loaded: supported venues first, then metrics, then the verdict, then pricing. Every sentence carries information, though the dense metric enumeration reads as a catalog rather than prose, which slightly costs readability.

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 correctly carries the return contract: it specifies the verdict values and the metric set the agent will receive. Cost and missing-data behavior are disclosed. Minor gaps remain, such as units/format of the LP-return figures and what happens for an unsupported or unindexed pool.

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 100% and there is only one parameter, so the schema already carries the burden; baseline is 3. The description does contribute a domain constraint by listing which AMM families the pool address must belong to, which is a useful semantic filter beyond the schema's bare pattern.

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 names the specific resource (pool health for Raydium AMM/CPMM/CLMM, Orca Whirlpool, Meteora DLMM, PumpSwap) and enumerates the exact metrics returned (depth within 2%, slippage at $1k/$10k, 24h liquidity flow, LP return vs holding at 7/30 days, bot/sandwich share) plus a verdict. That is far more specific than a tautology. It does not, however, differentiate itself from sibling clmm_range_stats or market_snapshot, so an agent must infer the boundary.

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?

There is no when-to-use statement, no prerequisites, and no explicit routing to or away from alternatives such as clmm_range_stats or market_snapshot. The list of supported AMMs implicitly scopes applicability, but the agent gets no guidance on choosing this tool over its siblings.

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