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

With no annotations, the description carries the full burden and does well: it discloses that evidence requests run concurrently, that no proposal is created, that ordering is a spiky spot rate rather than a durable yield, and that warnings and user execution eligibility are included. It does not cover rate limits, failure modes, or default thresholds, keeping it below 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?

Three sentences, all load-bearing: capability, ranking caveat, and execution semantics, with the key warning about spiky APY front-loaded rather than buried. The long criteria list in sentence one is dense but justified because it defines the ranking inputs.

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?

There is no output schema, yet the description names a concrete return field (evidence.apy.medianPercent) and explicitly defines the result ordering, which are the two things an agent most needs. It omits the exact shape of each ranked entry and pagination behavior beyond 'limit', a minor gap for a six-parameter read tool.

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 100%, so all six parameters are already documented in the schema, establishing a baseline of 3. The description adds interpretive value by implying what apyDays and tvlDays feed (APY median/average/range/volatility, TVL trend/drawdown) but never explicitly links those windows to the parameters or explains minTvlUsd/chainId behavior.

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 gives a specific verb and resource ('Batch-rank Morpho markets') plus the exact ranking criteria (net APY, APY median/range/volatility, TVL trend/drawdown, vault age, liquidity, eligibility). This clearly separates it from siblings like list_yield_markets (enumeration) and get_yield_market_detail (single market).

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 a concrete operating instruction: results are ordered by spot APY, so re-rank on evidence.apy.medianPercent before acting. It also clarifies scope ('never creates a proposal'), which tells the agent this is an analytical, pre-decision step. It stops short of naming sibling tools or exclusion conditions, so not a 5.

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