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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral detail beyond them: the returned composition (summary paragraph, weighted factor bullets, net-yield notes), the caveat that exitRisk is liquidity-only and not on-chain withdrawability, that medium often reflects confidence rather than pool size, and the VALIDATION_ERROR behavior for unknown chain keys with no invented bridge fee. It also flags 'Research only — non-custodial.'

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?

The purpose and the chaining instruction are front-loaded, and the embedded example is useful. Some sentences are heavy run-ons (the exitRisk parenthetical) and the alias and chain-key rules are repeated from the schema, costing a little density.

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, the description carries the load of saying what comes back and does so concretely, including the limits of the exitRisk heuristic. All six parameters are covered, the chaining source is named, and failure modes are called out — enough for an agent to call this correctly and interpret the result.

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 the baseline would be 3; the description earns credit by framing the id/poolId/opportunityId trio as interchangeable aliases sourced from list_yields[].id, which is workflow context the schema documents only in isolation. It restates the sourceChainKey restriction and the horizonDays/notionalUsd defaults, which is mostly redundant with the schema.

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 and resource: an agent-readable explanation of why an opportunity received its risk-adjusted score. It is clearly a read/justification tool rather than a scoring or comparison tool, though the contrast with the sibling score_opportunity is only implied ('prefer this when you need to justify a ranking') rather than stated outright.

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?

Gives concrete pre-call context: pass list_yields opportunities[].id as poolId/opportunityId/id, and pass protocolSlug to get_protocol_risk for further risk detail. It also says when to prefer it (justifying a ranking to a human or another agent). It does not explicitly exclude score_opportunity or compare_opportunities, so the boundary is clear but not fully closed.

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