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

With no annotations, the description carries the burden and discloses useful behaviors: NULL-tvl rows sort last, the data is from the same snapshot/pools reads, and the response is wrapped in a proof envelope. This goes beyond the bare operation but doesn't cover error/auth/rate-limit details, so a 4.

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?

Three short sentences, front-loaded with the operation, and no filler. Each sentence contributes a distinct fact (ranking, null ordering, envelope).

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 simple one-parameter read tool with no output schema, the description is complete: it states what is returned (top-N pools), ordering behavior, consistency with the snapshot, and the response envelope. It doesn't elaborate the envelope's internal fields, but that appears to be a shared convention among the sibling tools.

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?

The schema only has 'limit' (integer, default 10) with 0% description coverage, but the description's 'top-N' maps N directly to the limit parameter and the TVL ranking gives it meaning. It doesn't specify bounds or edge behavior for limit, but it compensates reasonably for a single simple parameter.

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 uses a specific verb ('Return') and resource ('AMM pools'), with clear ranking criterion ('tvl_usd') and scope ('top-N'). This distinguishes it from the sibling get_amm_pool, which targets individual pools.

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 establishes clear context: the results are top-ranked by TVL and come from the same snapshot/pools reads, so an agent can infer when to call it for rankings. However, it does not explicitly name alternatives or state when not to use it, so it stops short of a full 5.

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