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

With no annotations, the description carries the full burden and does disclose the key non-obvious behavioral fact: this is a paid call at $0.003 USDC per call settled via x402 on Base, which an agent must know before invoking. It also implies the data granularity (1d/7d change, 90 days of history), but says nothing about rate limits, error behavior, or data freshness.

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 core capability is front-loaded in one dense sentence that enumerates the modes in the same order an agent would reason about them, followed by a short payment notice. It is information-dense rather than padded, though the single mega-sentence packs three modes together and would read faster as a short list.

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?

For a 5-parameter tool with no output schema and no annotations, the description covers the critical unknowns: what data comes back per mode and that the call costs money. Gaps remain around result limits (maxItems default 10 is only in the schema), pagination, and the absence of an output schema means return shape for the chains mode is only loosely implied.

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 a 3 is the baseline; the description earns above that by explaining what each mode actually returns (protocols/chains/protocol) and by surfacing the fields available in protocol output (TVL, 1d/7d change, market cap, chains), giving the 'mode' and 'category' parameters real semantic weight. It does not clarify 'maxItems' or the name/slug format beyond what the schema 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?

The description names a specific resource (DeFi TVL from DefiLlama) and enumerates the three distinct output shapes it can return: filtered protocol lists, chain TVL rankings with protocol counts, and single-protocol per-chain splits with 90-day history. This clearly separates it from siblings like defi_pool, defi_summary, and defi_yields without needing to open the schema.

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?

The three modes are described with enough detail that an agent can infer which mode fits which question (ranked/filtered lists vs. chain-level rankings vs. deep-dive on one protocol). However, no sibling alternatives are named and no explicit exclusions ('use X instead when...') are given, so routing across the several other defi_* tools is left to inference.

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