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

No annotations exist, so the description carries the full burden. It discloses that sorting is available and what the sort keys mean, which is real behavioral context, but it never states that results are filtered by a default TVL floor of $1M (the schema default), whether data is live or cached, or whether results are capped by limit. For an unannotated read tool with a significant default filter, this is a notable gap.

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 sentences, front-loaded with the resource and metrics, then the sort options, then the use case. Every clause carries information; the protocol list is compressed into one parenthetical. No filler.

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?

Output schema exists, so return values need not be explained, and the description covers the core query surface. But with six parameters, no annotations, and multiple sibling tools in the DeFi space, missing details on limit/pagination and the min_tvl default leave the agent without enough to predict result truncation or unexplained empty results.

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 0%, so the description must compensate and largely does: it names the accepted sort values (supply_apy, borrow_apy with "cheapest first" semantics, tvl) for an enum-less string parameter, and maps "by token, chain or protocol" onto the symbol/chain/project filters. It omits limit and min_tvl_usd entirely, including the $1M default that silently excludes low-TVL markets, which keeps it from a 5.

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?

States a specific verb+resource: supply and borrow APYs across named DeFi lending protocols, broken down by token, chain or protocol, and enumerates the returned metrics (net borrow rate, utilisation, TVL, total borrowed, max LTV). An agent knows exactly what it gets. It does not name or contrast the nearest sibling (defi_yields, perp_funding_rates), 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?

"Use to find the best place to lend or borrow" gives an intended use, and "borrow_apy (cheapest first)" hints at the borrow-shopping case. But there is no when-not guidance, no mention of when to prefer defi_yields or perp_funding_rates instead, and no prerequisites. Usage is implied rather than specified.

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