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

With only readOnlyHint/destructiveHint on the annotations, the description carries real behavioral weight and delivers: a 60-second edge cache with cache.hit and cache.age_seconds, a ~1-hour measured (never annualised) window, dual denominators including a 2% tick-book reconstruction, and the fact that stale-but-funded tiers are reported. It stops short of failure modes or a full return-shape statement, so 4 rather than 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?

It is front-loaded with the use case before the methodology, and most sentences carry information. But it is a single dense paragraph of ~230 words for a one-parameter tool, with editorial asides ('which does not say which one pays', 'every interface shows') that inflate length without adding call-relevant facts.

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?

This is a methodologically complex tool with no output schema, so the description must explain returns; it names swaps, turnover, realized fees, fees per $1,000, both rankings, and the cache fields, and it discloses the measurement window. That is close to complete, though it does not enumerate the full response shape or error behavior.

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?

One parameter with 100% schema description coverage ('A BSC token address, or a PancakeSwap pool address to pin the pair'), so the schema already carries the semantics. The description explains the pair/pool context around the token but adds no syntax, format, or token-vs-pool behavioral detail beyond the schema; baseline 3 applies.

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 states a specific domain and measurement: a LP choosing where to place liquidity, and the tool measures each fee tier (V2 0.25%, V3 0.01/0.05/0.25/1.00%) over a live window with swaps, turnover, fees and fees-per-capital. That is a concrete verb+resource (rank PancakeSwap fee tiers for a pair), but it is delivered as a narrative rather than a crisp statement, and it never distinguishes itself from siblings like pancakeswap_position_look, pancakeswap_range_plan or bsc_pool_scan.

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 opening clause 'For a liquidity provider deciding WHERE to put liquidity' implies the use case, and it says both rankings are returned because they disagree. However, no explicit alternatives are named and there is no when-not guidance, so the agent must infer when this beats sibling tools.

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