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

With no annotations supplied, the description still carries the key behavioral facts: it is a paid call, the exact price and accepted payment networks, that no auth or API key is needed, that failures are not charged, and that data comes live from DefiLlama. Missing only rate limits, latency/freshness guarantees, and what an exhausted-payment or upstream-outage response looks like.

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 purpose and return fields are front-loaded in the first clause, followed by price/payment and then the endpoint URL. Every fragment earns its place for an agent deciding whether it can afford and call the tool; there is no filler.

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?

Given zero params, no annotations, and no output schema, the description covers what is returned (TVL plus 1d/7d/30d change), the data source, cost, and payment path. It stops short of stating the response shape or currency/units, which an agent must discover at call time.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless schema applies. The description correctly implies a fixed query (one chain, one metric, three change windows) rather than a configurable one.

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 verb ("buy"/paid fetch) and a specific resource: Morph's DeFi TVL with 1d/7d/30d change, sourced from DefiLlama. That distinguishes it from the many buy_tvl_<chain> siblings. It loses a point only because "Morph" vs the similarly named Morpho protocol siblings (buy_coin_MORPHO, buy_yields_protocol_morpho-blue) is never disambiguated.

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?

Access and payment conditions are explicit ($0.005 USDC on Base or Solana, no account, no API key, failed calls not charged), which tells the agent how to transact. But there is no explicit when-to-use guidance, no exclusions, and no named alternative such as buy_tvl_ethereum or buy_yields_chain_* for related queries; selection is left to inference from the chain name.

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