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

Goes well past the readOnlyHint/openWorldHint annotations: it discloses failure semantics ('fails and is not charged if the protocol isn't found or DeFi Llama doesn't answer') and pricing ('$0.005 USDC per call'). It also sets an interpretive guardrail — 'neutral facts, not a safety rating: audits don't mean a protocol is safe' — which prevents a plausible agent mistake.

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 long opening sentence front-loads the returned payload as a scannable list, and the following sentences carry only non-obvious constraints: parent-name behavior, neutrality caveat, failure/charge semantics, and price. It is dense but nearly every clause adds information; slightly list-heavy for a single breath.

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?

No output schema exists, so the description must explain the return payload — and it enumerates fields, including exploit sub-fields (date, amount lost/returned, classification, technique) and flags. With cost, failure behavior, and the neutrality caveat also covered, an agent has everything needed to call and interpret it.

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 already documents the single parameter at 100% coverage, including examples, so the baseline is 3. The description adds one genuine semantic detail beyond the schema: a parent protocol name resolves to all of its versions, which changes how an agent should interpret results for names like 'Aave'.

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?

Names a specific resource (DeFi protocol due-diligence facts) and enumerates the exact data returned: TVL with 1d/7d change, chain split, category, audits, exploits, and flags. An agent can distinguish it from token-level siblings like token_risk_score or dependency_risk_score because the description anchors to protocol-level DeFi Llama data.

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 input examples ('aave-v3', 'Aave', 'Jupiter Lend') and clarifies that a parent name covers all its versions, which is real selection guidance. It stops short of explicitly routing against alternatives such as token_risk_score or evm_token_security, so no exclusion clause exists.

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