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

Goes well beyond the annotations by disclosing commercial behavior: "$0.01/call via x402 USDC or a card key", "first 25 free", "failed calls free", and "each call is charged, so repeats are not free" — directly explaining the idempotentHint=false consequence. It also restates the no-side-effects contract ("reads or computes only and changes nothing"), which is consistent with readOnlyHint/destructiveHint rather than contradicting them.

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?

Purpose and modes are front-loaded and every clause carries information — outputs, filters, pricing, safety. The main weakness is that it is one long run-on sentence chain ("…top chains; or list…") with no separation between capability, billing, and safety, which makes it denser than it needs to be.

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, so the description carries the return-shape burden and does so: TVL, 1h/1d/7d change, market cap to TVL, top chains, or a ranked list. Combined with cost and safety disclosure, an agent has everything needed to call it correctly without surprises.

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 description coverage is 100%, so every parameter is already documented, and the description's parameter content is largely redundant (naming Aave/Lido/Uniswap as protocol examples, Lending/Dexs as category examples, tvl/1d/7d as sort values). Marginal added meaning is the protocol-versus-ranking framing, which the schema's protocol description already states.

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?

Opens with a specific verb+resource ("Total value locked of DeFi protocols from DefiLlama") and then spells out the two operating modes: single-protocol lookup versus ranked list. It even scopes out a whole category ("CEXs are left out unless asked for"). The only gap is that the near sibling defi_chains is never named, so an agent must infer which tool owns per-chain TVL rankings.

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 use cases ("size a protocol, compare competitors or track where liquidity moves") plus a worked example ("protocol=aave"). It implies when to leave protocol empty for a ranking. It stops short of explicit when-not/alternative routing, e.g. pointing chain-level questions at defi_chains.

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