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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description clears it by disclosing what is returned (ticks, TVL, 24h volume, pool-level fee APR) and how net APR is computed over the window. It doesn't mention pagination or result-size behavior, keeping it short of a 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?

Two tight sentences that front-load the ranking method before the return payload and filters. Dense but every clause carries information; the parenthetical formula is justified because the metric is the tool's core.

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 and 8 parameters, the description usefully spells out the returned fields and metric semantics, so an agent can interpret results. Pagination and ordering behavior are left to the schema, a minor gap rather than a blocking one.

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 63%, and the description compensates by explaining the window default (7 days/168h), the net APR sort basis, and the 'best price range' concept that ties into the range fields returned. It adds meaning beyond enum labels, though undocumented params like offset/limit remain schema-only.

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?

Starts with a specific verb+resource ('Active pools ranked by...') and defines the ranking metric precisely as net APR = fees − impermanent loss, which distinguishes it from peers like get_pool and find_pair_pools. An agent can identify this as the ranking/discovery tool without opening the schema.

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?

It states the filtering dimensions ('Filter by chain and pool class') and the default window, implying when the tool fits, but never contrasts itself with siblings such as find_pair_pools or get_pool or says when a single-pool lookup is preferable. Usage is inferable rather than explicit.

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